<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:googleplay="http://www.google.com/schemas/play-podcasts/1.0"><channel><title><![CDATA[Past Performance Lab]]></title><description><![CDATA[Past performance is no guarantee of future results. We check anyway.]]></description><link>https://www.pastperformancelab.com</link><image><url>https://substackcdn.com/image/fetch/$s_!jDh6!,w_256,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0939f4d1-f253-496c-919e-84b675c82eed_512x512.png</url><title>Past Performance Lab</title><link>https://www.pastperformancelab.com</link></image><generator>Substack</generator><lastBuildDate>Sat, 21 Nov 2026 05:59:40 GMT</lastBuildDate><atom:link href="https://www.pastperformancelab.com/feed" rel="self" type="application/rss+xml"/><copyright><![CDATA[Antoni Gaudi]]></copyright><language><![CDATA[en]]></language><webMaster><![CDATA[pastperformancelab@substack.com]]></webMaster><itunes:owner><itunes:email><![CDATA[pastperformancelab@substack.com]]></itunes:email><itunes:name><![CDATA[Antoni Gaudí]]></itunes:name></itunes:owner><itunes:author><![CDATA[Antoni Gaudí]]></itunes:author><googleplay:owner><![CDATA[pastperformancelab@substack.com]]></googleplay:owner><googleplay:email><![CDATA[pastperformancelab@substack.com]]></googleplay:email><googleplay:author><![CDATA[Antoni Gaudí]]></googleplay:author><itunes:block><![CDATA[Yes]]></itunes:block><item><title><![CDATA[What Would Actually Happen If You Bought Every 30% Crash?]]></title><description><![CDATA[The viral &#8220;3% chance of a loss&#8221; counts six crashes 1,008 times. Waiting for 30% falls since 1993 turned $10,000 into $48,000; SPY made $291,000.]]></description><link>https://www.pastperformancelab.com/p/buy-after-stock-market-crash-backtest</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/buy-after-stock-market-crash-backtest</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Fri, 20 Nov 2026 05:56:53 GMT</pubDate><enclosure url="https://substackcdn.com/image/fetch/$s_!ITNS!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3530e540-e1be-4021-870e-fe1c4de7b1aa_1280x974.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Issue 14 &#183; November 2026 &#183; 1 viral claim &#183; 6 crashes since 1950 &#183; 3 thresholds on SPY, 1993&#8211;2026</em></p><p>A <a href="https://www.youtube.com/watch?v=_oc9guYIdqA">Spanish-language YouTube video</a> says buying the S&amp;P 500 after a 30% fall loses money only 3% of the time over the next 12 months, with an average gain of 22%. The 3% is real, but the way it is counted is the trap.</p><p>It counts every trading day the index spent 30% below its peak as a separate bet: 1,008 days since 1950. Those days come from just six crashes, and the first buy lost money in two of them.</p><p>Run as a strategy, the wait cost more than the crashes paid. Since 1993, $10,000 that bought SPY only after a 30% fall grew to about $48,000; left in SPY, it grew to about $291,000.</p><p><strong>Verdict: FAIL, 0 of 3 thresholds pass. Buying SPY only after a 30%, 25% or 20% fall earned 4.84%, 5.74% and 6.76% a year; holding it earned 10.75%.</strong><br><em>SPY with dividends, 16 Nov 1993 &#8211; 13 Nov 2026, buy at the next open, hold 252 trading days, T-bill interest while waiting, 0.02% per buy or sell.</em></p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!ITNS!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3530e540-e1be-4021-870e-fe1c4de7b1aa_1280x974.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!ITNS!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3530e540-e1be-4021-870e-fe1c4de7b1aa_1280x974.png 424w, https://substackcdn.com/image/fetch/$s_!ITNS!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3530e540-e1be-4021-870e-fe1c4de7b1aa_1280x974.png 848w, https://substackcdn.com/image/fetch/$s_!ITNS!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3530e540-e1be-4021-870e-fe1c4de7b1aa_1280x974.png 1272w, https://substackcdn.com/image/fetch/$s_!ITNS!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3530e540-e1be-4021-870e-fe1c4de7b1aa_1280x974.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!ITNS!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3530e540-e1be-4021-870e-fe1c4de7b1aa_1280x974.png" width="1280" height="974" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/3530e540-e1be-4021-870e-fe1c4de7b1aa_1280x974.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:974,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:29764,&quot;alt&quot;:&quot;Chart: $10,000 held in SPY grew to about $291,000 from 16 Nov 1993 to 13 Nov 2026; buying SPY only after a 30% fall grew it to about $48,000.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Chart: $10,000 held in SPY grew to about $291,000 from 16 Nov 1993 to 13 Nov 2026; buying SPY only after a 30% fall grew it to about $48,000." title="Chart: $10,000 held in SPY grew to about $291,000 from 16 Nov 1993 to 13 Nov 2026; buying SPY only after a 30% fall grew it to about $48,000." srcset="https://substackcdn.com/image/fetch/$s_!ITNS!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3530e540-e1be-4021-870e-fe1c4de7b1aa_1280x974.png 424w, https://substackcdn.com/image/fetch/$s_!ITNS!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3530e540-e1be-4021-870e-fe1c4de7b1aa_1280x974.png 848w, https://substackcdn.com/image/fetch/$s_!ITNS!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3530e540-e1be-4021-870e-fe1c4de7b1aa_1280x974.png 1272w, https://substackcdn.com/image/fetch/$s_!ITNS!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3530e540-e1be-4021-870e-fe1c4de7b1aa_1280x974.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><h3>Three checks before you trust a &#8220;chance of losing&#8221; number</h3><ol><li><p><strong>Count the crashes, not the days.</strong> 1,008 days from six crashes are six results, not 1,008.</p></li><li><p><strong>Ask what the money does while it waits.</strong> This rule sat in T-bills 81.8% of the time, and the wait cost more than the crashes paid back.</p></li><li><p><strong>Compare it with holding the index from the same day.</strong> The rule won 5 of its 6 trades and still ended far behind.</p></li></ol><p>01 / THE CLAIM</p><h2>Six crashes, counted 1,008 times</h2><p>The video&#8217;s numbers roughly reproduce on the S&amp;P 500 price index since 1950. Of the 1,008 days at least 30% below the peak, 4.4% were followed by a 12-month loss, and the average gain was 20.0%.</p><p>Those days are not separate bets. Two crashes, 2001 and 2008, supplied 761 of them.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!p--V!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68fe8b70-cb08-4285-b863-059bd42b683b_1280x984.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!p--V!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68fe8b70-cb08-4285-b863-059bd42b683b_1280x984.png 424w, https://substackcdn.com/image/fetch/$s_!p--V!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68fe8b70-cb08-4285-b863-059bd42b683b_1280x984.png 848w, https://substackcdn.com/image/fetch/$s_!p--V!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68fe8b70-cb08-4285-b863-059bd42b683b_1280x984.png 1272w, https://substackcdn.com/image/fetch/$s_!p--V!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68fe8b70-cb08-4285-b863-059bd42b683b_1280x984.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!p--V!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68fe8b70-cb08-4285-b863-059bd42b683b_1280x984.png" width="1280" height="984" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/68fe8b70-cb08-4285-b863-059bd42b683b_1280x984.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:984,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:22247,&quot;alt&quot;:&quot;Chart: the 1,008 days split into six crashes: 412 days from 2001, 349 from 2008, 198 from 1974, 34 from 1970, 13 from 1987 and 2 from 2020; the first buy lost money in 2001 and 2008.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Chart: the 1,008 days split into six crashes: 412 days from 2001, 349 from 2008, 198 from 1974, 34 from 1970, 13 from 1987 and 2 from 2020; the first buy lost money in 2001 and 2008." title="Chart: the 1,008 days split into six crashes: 412 days from 2001, 349 from 2008, 198 from 1974, 34 from 1970, 13 from 1987 and 2 from 2020; the first buy lost money in 2001 and 2008." srcset="https://substackcdn.com/image/fetch/$s_!p--V!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68fe8b70-cb08-4285-b863-059bd42b683b_1280x984.png 424w, https://substackcdn.com/image/fetch/$s_!p--V!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68fe8b70-cb08-4285-b863-059bd42b683b_1280x984.png 848w, https://substackcdn.com/image/fetch/$s_!p--V!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68fe8b70-cb08-4285-b863-059bd42b683b_1280x984.png 1272w, https://substackcdn.com/image/fetch/$s_!p--V!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68fe8b70-cb08-4285-b863-059bd42b683b_1280x984.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p>Count each crash once, from its first close 30% below the peak, and the index lost money over the next 12 months in 2 of 6: &#8722;15.9% after September 2001 and &#8722;0.2% after October 2008.</p><p>With dividends, on the whole US market, all six first buys made money. Six results cannot carry a number like 3%.</p><p>02 / THE STRATEGY</p><h2>Waiting for the crash cost more than the crash paid</h2><p>We turned the claim into a rule anyone can follow with SPY. Buy at the next open after a close 30% below the all-time high, hold 252 trading days (about 12 months), and buy again if the index is still that low.</p><p>From 16 Nov 1993 to 13 Nov 2026, the rule bought 6 times and won 5, including +74.5% after March 2020. It was invested 18.2% of the time; the rest sat in T-bills.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!ymsM!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6abde417-b752-42a2-b7b9-ec0f125a0a5a_1280x990.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!ymsM!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6abde417-b752-42a2-b7b9-ec0f125a0a5a_1280x990.png 424w, https://substackcdn.com/image/fetch/$s_!ymsM!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6abde417-b752-42a2-b7b9-ec0f125a0a5a_1280x990.png 848w, https://substackcdn.com/image/fetch/$s_!ymsM!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6abde417-b752-42a2-b7b9-ec0f125a0a5a_1280x990.png 1272w, https://substackcdn.com/image/fetch/$s_!ymsM!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6abde417-b752-42a2-b7b9-ec0f125a0a5a_1280x990.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!ymsM!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6abde417-b752-42a2-b7b9-ec0f125a0a5a_1280x990.png" width="1280" height="990" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/6abde417-b752-42a2-b7b9-ec0f125a0a5a_1280x990.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:990,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:36518,&quot;alt&quot;:&quot;Table: buying SPY only after a 30%, 25% or 20% fall turned $10,000 into about $48,000, $63,000 and $86,000 from 16 Nov 1993 to 13 Nov 2026; holding SPY made about $291,000. All three fail.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: buying SPY only after a 30%, 25% or 20% fall turned $10,000 into about $48,000, $63,000 and $86,000 from 16 Nov 1993 to 13 Nov 2026; holding SPY made about $291,000. All three fail." title="Table: buying SPY only after a 30%, 25% or 20% fall turned $10,000 into about $48,000, $63,000 and $86,000 from 16 Nov 1993 to 13 Nov 2026; holding SPY made about $291,000. All three fail." srcset="https://substackcdn.com/image/fetch/$s_!ymsM!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6abde417-b752-42a2-b7b9-ec0f125a0a5a_1280x990.png 424w, https://substackcdn.com/image/fetch/$s_!ymsM!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6abde417-b752-42a2-b7b9-ec0f125a0a5a_1280x990.png 848w, https://substackcdn.com/image/fetch/$s_!ymsM!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6abde417-b752-42a2-b7b9-ec0f125a0a5a_1280x990.png 1272w, https://substackcdn.com/image/fetch/$s_!ymsM!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6abde417-b752-42a2-b7b9-ec0f125a0a5a_1280x990.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p>That idle cash is the cost. On $10,000, waiting for 30% falls ended about $243,000 behind holding SPY.</p><p>Lower thresholds buy more often and still trail: 5.74% a year at 25% and 6.76% at 20%, against 10.75% for SPY.</p><p>03 / ON TOP OF SPY</p><h2>As an add-on, a little more return and a deeper fall</h2><p>The other way to use the signal is a top-up: hold SPY in full and borrow to buy as much again after a crash. The fair opponent is steady leverage, which borrows the same average amount every day, as in <a href="https://www.pastperformancelab.com/p/buy-the-dip-strategy-backtest-leverage">Issue 13</a>.</p><p>At 30%, the top-up earned 11.75% a year against 11.62% for steady leverage. Its worst fall was &#8722;75.3%, 12.9 points deeper than steady leverage&#8217;s &#8722;62.4%.</p><p>At 25% it earned less than steady leverage, 11.86% against 12.25%. At 20% it earned a little more, 12.65% against 12.48%, with a fall 9.8 points deeper.</p><p>So the add-on fails as well. Its extra return came with a deeper hole.</p><p>04 / SHOULD YOU USE IT</p><h2>What survives, and what to do on Monday</h2><p>What survives: on average, days 30% below the peak were followed by better years than the average day since 1950, 20.0% against 9.5%. Money you were going to invest anyway did well going in after a fall.</p><p>What fails is the wait. Over 33 years, the cash held back for the next crash cost far more than the crashes paid.</p><p>Monday&#8217;s version: if you hold an index fund, this test gives no reason to sell and wait for the next crash.</p><div class="subscription-widget-wrap-editor" data-attrs="{&quot;url&quot;:&quot;https://www.pastperformancelab.com/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe&quot;,&quot;language&quot;:&quot;en&quot;}" data-component-name="SubscribeWidgetToDOM"><div class="subscription-widget show-subscribe"><div class="preamble"><p class="cta-caption">One strategy tested every Tuesday. Free.</p></div><form class="subscription-widget-subscribe"><input type="email" class="email-input" name="email" placeholder="Type your email&#8230;" tabindex="-1"><input type="submit" class="button primary" value="Subscribe"><div class="fake-input-wrapper"><div class="fake-input"></div><div class="fake-button"></div></div></form></div></div><h3>Your turn</h3><p>Send us the strategy you are about to risk money on. Reply to this email or write to pastperformancelab@protonmail.com.</p><div><hr></div><h3>Method</h3><ul><li><p><strong>Pass rule, written 16 Nov 2026, before the run.</strong> Each threshold had to beat SPY&#8217;s annual return on its own: full window, next-open fills, costs charged once. One test per threshold, each judged alone.</p></li><li><p><strong>Signal.</strong> The fall is measured on SPY&#8217;s price without dividends, from its all-time closing high, as the claim measures it. Buy when the close is 30% (25%, 20%) or more below; hold 252 sessions; buy again if it is still below.</p></li><li><p><strong>Returns.</strong> SPY with dividends reinvested, fills at the next open, 0.02% per buy or sell, daily T-bill interest on cash. Window 16 Nov 1993 &#8211; 13 Nov 2026, after a 200-session warmup.</p></li><li><p><strong>Top-up, reported only.</strong> It doubles SPY with borrowed money for the 252 sessions after each signal, at the T-bill rate plus 1.5 points. Steady leverage holds 1 + E times SPY every day, where E is the share of sessions with the top-up on, at the same rate.</p></li><li><p><strong>The 3% check.</strong> S&amp;P 500 price index (^GSPC), 3 Jan 1950 &#8211; 12 Nov 2026, 12 calendar months forward. With dividends: the Fama-French US market series to 30 Jun 2026.</p></li><li><p>The video&#8217;s author is welcome to reply; we will publish any answer in full.</p></li></ul><p>Full method: <a href="https://www.pastperformancelab.com/p/how-we-backtest-trading-strategies">How We Test a Trading Strategy</a>.</p><p><em>Past performance is no guarantee of future results. We check anyway.</em></p><p><em>This is research on historical data, not investment advice. <a href="https://www.pastperformancelab.com/about">Full disclaimer</a>.</em></p>]]></content:encoded></item><item><title><![CDATA[Your Paper Trades May Be Running on Delayed Prices]]></title><description><![CDATA[Ours ran four weeks on 10-minute-old futures prices, and nothing said so. Three checks before you trust a paper result.]]></description><link>https://www.pastperformancelab.com/p/paper-trading-delayed-market-data</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/paper-trading-delayed-market-data</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Tue, 17 Nov 2026 12:02:28 GMT</pubDate><enclosure url="https://substackcdn.com/image/fetch/$s_!8x5v!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70f462b1-9c3a-4675-9c4d-2619ba9dfd19_1360x830.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Issue 12 &#183; November 2026 &#183; 32 sessions, 1,209 ten-minute bars</em></p><p>Most traders test a strategy on a paper account before risking money. If its prices arrive late, the test measures the wrong thing, and nothing on screen tells you.</p><p>For four weeks in September our paper account traded a futures strategy on prices that were ten minutes old. The engine logged errors when bars failed to arrive, but not one message said the data was delayed.</p><p>We found it by comparing every decision with the finished bar after the close. The gap was too steady to be noise, and almost any retail setup can fall into it.</p><p><strong>Verdict: a paper test on delayed data tests the data, not the strategy.</strong><br><em>Method: 17 NYSE sessions on 10-minute-delayed CME data (2&#8211;25 Sep 2026) vs 15 sessions on real-time data (28 Sep&#8211;16 Oct), Micro Nasdaq futures, every 10-minute decision bar compared with the settled bar.</em></p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!8x5v!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70f462b1-9c3a-4675-9c4d-2619ba9dfd19_1360x830.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!8x5v!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70f462b1-9c3a-4675-9c4d-2619ba9dfd19_1360x830.png 424w, https://substackcdn.com/image/fetch/$s_!8x5v!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70f462b1-9c3a-4675-9c4d-2619ba9dfd19_1360x830.png 848w, https://substackcdn.com/image/fetch/$s_!8x5v!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70f462b1-9c3a-4675-9c4d-2619ba9dfd19_1360x830.png 1272w, https://substackcdn.com/image/fetch/$s_!8x5v!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70f462b1-9c3a-4675-9c4d-2619ba9dfd19_1360x830.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!8x5v!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70f462b1-9c3a-4675-9c4d-2619ba9dfd19_1360x830.png" width="1360" height="830" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/70f462b1-9c3a-4675-9c4d-2619ba9dfd19_1360x830.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:830,&quot;width&quot;:1360,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:74947,&quot;alt&quot;:&quot;Table: on delayed data (2&#8211;25 Sep 2026, 17 sessions, 618 bars) the median gap between the decision close and the settled close was 13.25 points; 18.4% of bars (114) came within 5 points, 0.5% (3) matched exactly, and 9 signals flipped, 3 in the entry window. On real-time data (28 Sep&#8211;16 Oct, 15 sessions, 591 bars) every gap was 0.00 and no signal flipped.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: on delayed data (2&#8211;25 Sep 2026, 17 sessions, 618 bars) the median gap between the decision close and the settled close was 13.25 points; 18.4% of bars (114) came within 5 points, 0.5% (3) matched exactly, and 9 signals flipped, 3 in the entry window. On real-time data (28 Sep&#8211;16 Oct, 15 sessions, 591 bars) every gap was 0.00 and no signal flipped." title="Table: on delayed data (2&#8211;25 Sep 2026, 17 sessions, 618 bars) the median gap between the decision close and the settled close was 13.25 points; 18.4% of bars (114) came within 5 points, 0.5% (3) matched exactly, and 9 signals flipped, 3 in the entry window. On real-time data (28 Sep&#8211;16 Oct, 15 sessions, 591 bars) every gap was 0.00 and no signal flipped." srcset="https://substackcdn.com/image/fetch/$s_!8x5v!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70f462b1-9c3a-4675-9c4d-2619ba9dfd19_1360x830.png 424w, https://substackcdn.com/image/fetch/$s_!8x5v!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70f462b1-9c3a-4675-9c4d-2619ba9dfd19_1360x830.png 848w, https://substackcdn.com/image/fetch/$s_!8x5v!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70f462b1-9c3a-4675-9c4d-2619ba9dfd19_1360x830.png 1272w, https://substackcdn.com/image/fetch/$s_!8x5v!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70f462b1-9c3a-4675-9c4d-2619ba9dfd19_1360x830.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><h3>Three checks before you trust a paper result</h3><ol><li><p><strong>Ask your platform which feed you are on.</strong> In the IBKR API, <code>reqMarketDataType</code> sets the feed you ask for, and the market-data-type message tells you which one you got: 1 is live, 3 is delayed. That message answers a <code>reqMktData</code> request, so make one at startup and log the result.</p></li><li><p><strong>Check the newest bar's last trade time against the clock.</strong> On a delayed feed the bar's label still looks right. Compare the time of its last trade, or the latest tick, with the clock at the boundary; if it lags by more than a few seconds, you are behind.</p></li><li><p><strong>Compare each decision with the settled bar after the close.</strong> Count how often the signal would have changed. Zero is the target; ours was 9 in 618, 3 of them inside the entry window.</p></li></ol><p><code>01 / WHAT HAPPENED</code></p><h2>The account was never sent real-time prices, and nothing said so</h2><p>Our paper lane runs the Saty Phase Oscillator strategy from <a href="https://www.pastperformancelab.com/p/saty-phase-oscillator-backtest-out-of-sample">Issue 06</a> on 10-minute bars of Micro Nasdaq futures at Interactive Brokers. An IBKR paper account has no real-time exchange data of its own; it borrows the live account's subscriptions, if they are shared. Ours had none for CME futures, so IBKR served the free feed, ten minutes behind.</p><p>The bar requests our engine relied on never mentioned the delay. Two requests it never made would have: a live-quote request (IBKR Error 354) and a real-time-bars request (Error 420).</p><p><code>02 / WHAT IT DID</code></p><h2>Each decision used the previous bar plus a few seconds</h2><p>At each 10-minute boundary the engine took the newest finished bar. On a feed ten minutes late, that &#8220;newest&#8221; bar was really the one before, holding only its first seconds of trading, yet it looked complete and carried the right time.</p><p>Across 618 decision bars, the price the engine acted on sat a median of about 13 points from the bar that actually settled. Fewer than one bar in five came within 5 points (114 of 618). On 9 bars the settled bar would have changed the signal itself, 3 of them inside the entry window.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!6rlb!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa80ad1f6-12d9-4b65-9323-196be9f3f0d6_1360x1080.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!6rlb!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa80ad1f6-12d9-4b65-9323-196be9f3f0d6_1360x1080.png 424w, https://substackcdn.com/image/fetch/$s_!6rlb!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa80ad1f6-12d9-4b65-9323-196be9f3f0d6_1360x1080.png 848w, https://substackcdn.com/image/fetch/$s_!6rlb!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa80ad1f6-12d9-4b65-9323-196be9f3f0d6_1360x1080.png 1272w, https://substackcdn.com/image/fetch/$s_!6rlb!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa80ad1f6-12d9-4b65-9323-196be9f3f0d6_1360x1080.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!6rlb!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa80ad1f6-12d9-4b65-9323-196be9f3f0d6_1360x1080.png" width="1360" height="1080" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/a80ad1f6-12d9-4b65-9323-196be9f3f0d6_1360x1080.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1080,&quot;width&quot;:1360,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:71769,&quot;alt&quot;:&quot;Chart: median gap per session between decision close and settled close. Delayed sessions (2&#8211;25 Sep) sit between about 10 and 19 points, all-bars median 13.25; every real-time session (28 Sep&#8211;16 Oct) sits at 0.00.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Chart: median gap per session between decision close and settled close. Delayed sessions (2&#8211;25 Sep) sit between about 10 and 19 points, all-bars median 13.25; every real-time session (28 Sep&#8211;16 Oct) sits at 0.00." title="Chart: median gap per session between decision close and settled close. Delayed sessions (2&#8211;25 Sep) sit between about 10 and 19 points, all-bars median 13.25; every real-time session (28 Sep&#8211;16 Oct) sits at 0.00." srcset="https://substackcdn.com/image/fetch/$s_!6rlb!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa80ad1f6-12d9-4b65-9323-196be9f3f0d6_1360x1080.png 424w, https://substackcdn.com/image/fetch/$s_!6rlb!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa80ad1f6-12d9-4b65-9323-196be9f3f0d6_1360x1080.png 848w, https://substackcdn.com/image/fetch/$s_!6rlb!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa80ad1f6-12d9-4b65-9323-196be9f3f0d6_1360x1080.png 1272w, https://substackcdn.com/image/fetch/$s_!6rlb!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa80ad1f6-12d9-4b65-9323-196be9f3f0d6_1360x1080.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p><code>03 / THE FIX</code></p><h2>A small data subscription and bars we build ourselves</h2><p>The fix cost USD 1.55 a month: the CME real-time data package on the live account, shared with the paper account. We also changed the engine to build each 10-minute bar from the 1-minute stream, so a bar counts only when all ten of its minutes are in.</p><p>Since then, across 591 bars to 16 October, the bar the engine decided on was the bar that settled, every time; no signal flipped. Part of that match comes from building both from the same 1-minute stream, so read it as &#8220;the engine now waits for the finished bar&#8221;, not as a measure of the feed.</p><p><code>04 / WHY IT MATTERS</code></p><h2>Fills were real; decisions were not</h2><p>The paper fills always came at real-time prices, so the P&amp;L looked like trading while the signals came from the past. That is the danger: plausible results get no second look. A backtest always sees the finished bar; live, you get it only with real-time data and code that waits for the close.</p><div class="subscription-widget-wrap-editor" data-attrs="{&quot;url&quot;:&quot;https://www.pastperformancelab.com/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe&quot;,&quot;language&quot;:&quot;en&quot;}" data-component-name="SubscribeWidgetToDOM"><div class="subscription-widget show-subscribe"><div class="preamble"><p class="cta-caption">One strategy tested every Tuesday. Free.</p></div><form class="subscription-widget-subscribe"><input type="email" class="email-input" name="email" placeholder="Type your email&#8230;" tabindex="-1"><input type="submit" class="button primary" value="Subscribe"><div class="fake-input-wrapper"><div class="fake-input"></div><div class="fake-button"></div></div></form></div></div><h3>Your turn</h3><p>Send us the strategy you are about to risk money on, or the paper result you are about to trust. Reply to this email or write to pastperformancelab@protonmail.com. The first reader submission becomes Reader Test #1.</p><div><hr></div><h3>Method</h3><ul><li><p>Instrument and strategy: MNQ (Micro E-mini Nasdaq-100 futures), September 2026 contract until the 11 Sep roll, then December; Saty Phase Oscillator rules as in Issue 06; 10-minute bars, regular trading hours.</p></li><li><p>Delayed period: 2&#8211;25 Sep 2026, 17 sessions, 618 bars; 7 Sep (Labor Day, NYSE closed) excluded. 22 Sep has one bar: counted in the totals, left out of the per-session medians.</p></li><li><p>Real-time period: 28 Sep&#8211;16 Oct 2026, 15 sessions, 591 bars, engine building bars from 1-minute data.</p></li><li><p>Measure: the absolute gap between the close the engine decided on and the settled close, re-read after the session (16:20 ET from 16 Sep; the 2&#8211;15 Sep sessions on 16 Sep). &#8220;Within 5 points&#8221; includes 5.00. A &#8220;flip&#8221; is a bar where the settled bar would have changed the signal.</p></li><li><p>Not affected: every backtest and published verdict (Dukascopy and settled data), and the paper fills (real-time prices).</p></li><li><p>Source: our IBKR paper account's event log (derived statistics only).</p></li></ul><p>Full method: <a href="https://www.pastperformancelab.com/p/how-we-backtest-trading-strategies">How We Test a Trading Strategy</a>.</p><p><em>Past performance is no guarantee of future results. We check anyway.</em></p><p><em>This is research on historical data, not investment advice. <a href="https://www.pastperformancelab.com/about">Full disclaimer</a>.</em></p>]]></content:encoded></item><item><title><![CDATA[The Scoreboard: Every Strategy Against the Index]]></title><description><![CDATA[Popular trading strategies, tested with costs against simply holding the index. One plain-English block each, newest first.]]></description><link>https://www.pastperformancelab.com/p/backtested-trading-strategies-vs-buy-and-hold</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/backtested-trading-strategies-vs-buy-and-hold</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Sun, 15 Nov 2026 14:18:13 GMT</pubDate><enclosure url="https://substackcdn.com/image/fetch/$s_!jDh6!,w_256,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0939f4d1-f253-496c-919e-84b675c82eed_512x512.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Updated 20 November 2026 &#183; 14 tests, newest first</em></p><p>This page lists every trading strategy we have tested, in plain English. Read each line as the claim, then our result, then how it did against simply holding the index, then our verdict. The lesson so far: none has cleanly beaten simply holding the index once trading costs and idle cash count.</p><p>Holding the index means buying one fund that tracks the market, such as SPY or QQQ, and doing nothing. Idle cash is money a strategy keeps out of the market while it waits for a signal.</p><p>How each test works is on our <a href="https://www.pastperformancelab.com/p/how-we-backtest-trading-strategies">method page</a>.</p><div><hr></div><h3>14 &#183; Buying SPY after a 30% fall from its all-time high and holding 12 months; also tested at 25% and 20%</h3><ul><li><p><strong>The claim:</strong> Buying the S&amp;P 500 after a 30% fall loses money only 3% of the time over the next 12 months, with an average gain of 22%.</p></li><li><p><strong>Our result:</strong> The 3% counts 1,008 days from just six crashes, and the first buy lost money in two of them. As a rule on SPY since 1993 it won 5 of 6 trades, yet $10,000 grew to about $48,000; left in SPY, it grew to about $291,000.</p></li><li><p><strong>Against the index:</strong> Buying only after a 30%, 25% or 20% fall earned 4.84%, 5.74% and 6.76% a year; holding SPY earned 10.75%.</p></li><li><p><strong>Verdict:</strong> <strong>All three thresholds fail.</strong></p></li><li><p><strong>Should you use it?</strong> <strong>No.</strong> If you hold an index fund, this test gives no reason to sell and wait for the next crash. The borrowed top-up version fails too.</p></li></ul><p><em>Source: A Spanish-language YouTube video. Full test: <a href="https://www.pastperformancelab.com/p/buy-after-stock-market-crash-backtest">What Would Actually Happen If You Bought Every 30% Crash?</a>.</em></p><h3>13 &#183; Four dip-buying rules as top-ups on QQQ: Williams %R(2), KAMA(5) mean reversion, Triple RSI, Connors RSI(2)</h3><ul><li><p><strong>The claim:</strong> Buying the dip with borrowed money beats borrowing steadily.</p></li><li><p><strong>Our result:</strong> All four out-earned steady leverage: the top-ups ranged from about $166,000 (Triple RSI) to $471,000 (KAMA). But the pass rule, written before the test ran, also required no deeper fall. KAMA and Connors RSI(2) cleared it; Williams %R missed by 1.1 points and Triple RSI by 0.5.</p></li><li><p><strong>Against the index:</strong> Steady leverage with KAMA borrowing made about $234,000, and two of the four fell deeper than it did.</p></li><li><p><strong>Verdict:</strong> <strong>Two passed, two fell deeper.</strong></p></li><li><p><strong>Should you use it?</strong> <strong>Only as an add-on.</strong> Only as a top-up on an index you already hold. Williams %R needs a buy at the closing price, not the next morning.</p></li></ul><p><em>Source: Quantified Strategies; Larry Connors and Cesar Alvarez. Full test: <a href="https://www.pastperformancelab.com/p/buy-the-dip-strategy-backtest-leverage">Four Dip-Buying Rules Out-Earned Leverage. Only Two Passed.</a>.</em></p><h3>12 &#183; Paper trading on delayed prices: our own IBKR paper account on Micro Nasdaq futures</h3><ul><li><p><strong>The claim:</strong> Test a strategy on a paper account before you risk money.</p></li><li><p><strong>Our result:</strong> For four weeks our paper account traded on futures prices ten minutes old, and nothing said so. On 9 of 618 decision bars the settled bar would have changed the signal.</p></li><li><p><strong>Against the index:</strong> Not applicable: this is research about data, not a strategy.</p></li><li><p><strong>Verdict:</strong> <strong>Check the feed before trusting paper.</strong></p></li><li><p><strong>Should you use it?</strong> <strong>Not a strategy (data research).</strong> The post lists three checks before you trust a paper result.</p></li></ul><p><em>Source: Our paper lane (Saty Phase Oscillator, Issue 06). Full test: <a href="https://www.pastperformancelab.com/p/paper-trading-delayed-market-data">Your Paper Trades May Be Running on Delayed Prices</a>.</em></p><h3>11 &#183; 8/21 EMA crossover: buy the first dip after the 8-day exponential moving average crosses above the 21-day</h3><ul><li><p><strong>The claim:</strong> The strategy that "will help you retire".</p></li><li><p><strong>Our result:</strong> Each trade earns a little, and it roughly halves the worst fall. But it is in the market only a little over half the days. $10,000 on SPY from 1993 became $49,923.</p></li><li><p><strong>Against the index:</strong> Holding SPY turned the same $10,000 into $316,014. On QQQ: $60,501 against $167,199.</p></li><li><p><strong>Verdict:</strong> <strong>Trails the index.</strong></p></li><li><p><strong>Should you use it?</strong> <strong>No.</strong></p></li></ul><p><em>Source: <a href="https://x.com/RealJGBanks/status/2082265013948133722">Justin Banks on X</a>. Full test: <a href="https://www.pastperformancelab.com/p/8-21-ema-crossover-strategy-backtest">The 8/21 Pullback, a Sixth of the Money</a>.</em></p><h3>10 &#183; Triple RSI: buy the S&amp;P 500 fund after a three-day slide in a short-term momentum gauge</h3><ul><li><p><strong>The claim:</strong> Wins about 90% of its trades.</p></li><li><p><strong>Our result:</strong> The 90% is real: 82 winners in 91 trades. But the money sits in cash 95% of the time. $10,000 became about $70,500 from 1993 to 2026.</p></li><li><p><strong>Against the index:</strong> Simply holding the index fund turned the same $10,000 into about $298,000.</p></li><li><p><strong>Verdict:</strong> <strong>Claim true; trails the index alone.</strong></p></li><li><p><strong>Should you use it?</strong> <strong>Only as an add-on.</strong> As a top-up on an index you already hold, with borrowed money; it does nothing in a crash.</p></li></ul><p><em>Source: <a href="https://quantifiedstrategies.substack.com/p/triple-rsi-trading-strategy-enhance">Quantified Strategies</a>. Full test: <a href="https://www.pastperformancelab.com/p/triple-rsi-strategy-backtest">Nine Wins in Ten, a Quarter of the Money</a>.</em></p><h3>09 &#183; Free Dukascopy one-minute price data, used in many free backtests</h3><ul><li><p><strong>The claim:</strong> Free one-minute index data, downloadable for years back with one command.</p></li><li><p><strong>Our result:</strong> In 2013 about one minute in ten is a placeholder: a flat candle written when no price arrived. The files also show prices on 84 days the New York Stock Exchange was closed.</p></li><li><p><strong>Against the index:</strong> Not applicable: this is research about data, not a strategy.</p></li><li><p><strong>Verdict:</strong> <strong>Clean free data before backtesting.</strong></p></li><li><p><strong>Should you use it?</strong> <strong>Not a strategy (data research).</strong> The post includes a free 37-line checker.</p></li></ul><p><em>Source: Dukascopy free historical data. Full test: <a href="https://www.pastperformancelab.com/p/dukascopy-data-placeholder-minutes-backtest">One in Ten Minutes of Free 2013 Nasdaq-100 CFD Data Is a Placeholder</a>.</em></p><h3>08 &#183; 5-minute opening range breakout with a gap filter (and fixes tried on UT Bot, Nadaraya-Watson and TTM Squeeze)</h3><ul><li><p><strong>The claim:</strong> A popular day-trading rule: buy or sell the direction of the first five minutes.</p></li><li><p><strong>Our result:</strong> We tried twelve fixes on four failed strategies. Only a gap filter brought one back: the average trade more than doubled. The evidence is borderline and fades when orders fill late.</p></li><li><p><strong>Against the index:</strong> Alone, it turned $10,000 into a fraction of what QQQ made. Kept on top of a QQQ holding, it beat QQQ by several points a year, before real-world delays.</p></li><li><p><strong>Verdict:</strong> <strong>Borderline; helps only beside QQQ.</strong></p></li><li><p><strong>Should you use it?</strong> <strong>Only as an add-on.</strong> And only if its edge survives your real fill speed.</p></li></ul><p><em>Source: Carlo Zarattini and Andrew Aziz, Can Day Trading Really Be Profitable? (2023). Full test: <a href="https://www.pastperformancelab.com/p/opening-range-breakout-backtest-gap-filter">Not a Winner. Maybe a Sidekick.</a>.</em></p><h3>07 &#183; Three earlier strategies re-priced at the speed you can really trade</h3><ul><li><p><strong>The claim:</strong> Every backtest fills your order the instant a price bar closes.</p></li><li><p><strong>Our result:</strong> A 47-second delay, the speed of our own automated orders, cost 9 to 16% of profit. At two minutes late, the breakout's edge stopped looking real.</p></li><li><p><strong>Against the index:</strong> Not an index test: this issue measures what waiting costs.</p></li><li><p><strong>Verdict:</strong> <strong>Delay is a cost; test it.</strong></p></li><li><p><strong>Should you use it?</strong> <strong>Not a strategy (data research).</strong></p></li></ul><p><em>Source: Strategies from Issues 01 and 06. Full test: <a href="https://www.pastperformancelab.com/p/backtest-vs-live-trading-47-second-delay">The 47-Second Tax</a>.</em></p><h3>06 &#183; Saty Phase Oscillator, a Nasdaq day-trading signal (the strategy in our own paper account)</h3><ul><li><p><strong>The claim:</strong> Over the full history: less money than the index, much less risk.</p></li><li><p><strong>Our result:</strong> Strong on the years it was tuned on: 12.06% a year. On the years it never saw: 4.27% a year, on too few trades to call.</p></li><li><p><strong>Against the index:</strong> The Nasdaq 100 made 20.52% a year in the tuned years and 17.11% in the unseen years.</p></li><li><p><strong>Verdict:</strong> <strong>Unproven.</strong></p></li><li><p><strong>Should you use it?</strong> <strong>No.</strong> Not until it beats the index on years it never saw.</p></li></ul><p><em>Source: Saty Phase Oscillator, as run in the Lab's paper account. Full test: <a href="https://www.pastperformancelab.com/p/saty-phase-oscillator-backtest-out-of-sample">We Broke Our Own Strategy</a>.</em></p><h3>05 &#183; Connors RSI(2): buy the S&amp;P 500 after a sharp two- or three-day drop, sell on the bounce</h3><ul><li><p><strong>The claim:</strong> One of the most reposted dip-buying rules, and it wins 73% of its trades.</p></li><li><p><strong>Our result:</strong> The edge is real, but the money is in the market only about a tenth of the time. An account running it made 4.47% a year.</p></li><li><p><strong>Against the index:</strong> Holding the index made 12.71% a year. One dollar became $4.95 holding the index and $1.79 with the strategy.</p></li><li><p><strong>Verdict:</strong> <strong>Real edge, loses to the index.</strong></p></li><li><p><strong>Should you use it?</strong> <strong>Only as an add-on.</strong> Kept on top of an index holding it added return, with borrowed money and more risk.</p></li></ul><p><em>Source: Larry Connors and Cesar Alvarez, Short Term Trading Strategies That Work (2008). Full test: <a href="https://www.pastperformancelab.com/p/connors-rsi-2-backtest-vs-buy-and-hold">The Winner That Doesn't Win</a>.</em></p><h3>04 &#183; Industry trend following, tested over 100 years</h3><ul><li><p><strong>The claim:</strong> 18.2% a year for a hundred years.</p></li><li><p><strong>Our result:</strong> It replicates: we got 18.27%. But 63% of the growth came before 1980. The version you can actually buy, with sector funds, made 7.97% a year, and 5.85% once retail borrowing costs and trading costs count.</p></li><li><p><strong>Against the index:</strong> Over those same fund years, 2006 to 2026, the market made 11.37% a year.</p></li><li><p><strong>Verdict:</strong> <strong>Replicates; loses to the index today.</strong></p></li><li><p><strong>Should you use it?</strong> <strong>No.</strong></p></li></ul><p><em>Source: <a href="https://concretumgroup.com/a-century-of-profitable-industry-trends/">Carlo Zarattini and Gary Antonacci, A Century of Profitable Industry Trends</a>. Full test: <a href="https://www.pastperformancelab.com/p/industry-trend-following-100-year-backtest">The Century That Ended in 1990</a>.</em></p><h3>03 &#183; Weekly SPX put credit spread: an options trade that collects a small payment each week unless the S&amp;P 500 falls far</h3><ul><li><p><strong>The claim:</strong> Wins 95.4% of its weeks, with a worst fall of $4,605 on one contract since May 2020.</p></li><li><p><strong>Our result:</strong> The win rate is real. Run the same rule from 2013 and the worst fall grows five to ten times, to between $22,837 and $46,136. Three of the four worst weeks came just before the backtest starts.</p></li><li><p><strong>Against the index:</strong> The post does not compare it with holding the index. Its point is the hidden risk.</p></li><li><p><strong>Verdict:</strong> <strong>Win rate real, risk understated.</strong></p></li><li><p><strong>Should you use it?</strong> <strong>Maybe.</strong> Only with far more capital than the published $4,605 worst case suggests.</p></li></ul><p><em>Source: <a href="https://x.com/MrMilkTrading/status/2088011906384552045">The Milk Man (@MrMilkTrading)</a>. Full test: <a href="https://www.pastperformancelab.com/p/spx-put-credit-spread-backtest-2020">The Missing Ten Weeks</a>.</em></p><h3>02 &#183; Day-trading strategies opened up by the end of the $25,000 pattern-day-trader rule</h3><ul><li><p><strong>The claim:</strong> The $25,000 minimum for day trading is gone, so small accounts can now day-trade.</p></li><li><p><strong>Our result:</strong> The rule opened a door, not an edge. One trailing-stop strategy took 54,545 trades in thirteen years and lost about $940,000 per contract, mostly to costs. A published opening-range test fell from $138,639 to $4,860 once realistic slippage, the gap between the price you see and the price you get, was charged.</p></li><li><p><strong>Against the index:</strong> The post does not compare these strategies with holding the index. They fail on costs before that question comes up.</p></li><li><p><strong>Verdict:</strong> <strong>Fails under realistic slippage.</strong></p></li><li><p><strong>Should you use it?</strong> <strong>No.</strong></p></li></ul><p><em>Source: FINRA rule change. Full test: <a href="https://www.pastperformancelab.com/p/pdt-rule-replaced-day-trading-backtest">The $25,000 Door</a>.</em></p><h3>01 &#183; Five popular strategies: Connors RSI(2), the 5-minute opening range breakout, UT Bot, TTM Squeeze and the Nadaraya-Watson envelope</h3><ul><li><p><strong>The claim:</strong> Five popular strategies, each shared online with its full rules.</p></li><li><p><strong>Our result:</strong> Four failed once trading costs and a fair comparison were counted. Only Connors RSI(2) survived, trade by trade.</p></li><li><p><strong>Against the index:</strong> The survivor, Connors RSI(2), made $115,925 per contract. Simply holding the index made $291,484 over the same years, more than double.</p></li><li><p><strong>Verdict:</strong> <strong>Four fail, one survives per trade.</strong></p></li><li><p><strong>Should you use it?</strong> <strong>No.</strong> Issue 05 replaced the Connors verdict: read that first.</p></li></ul><p><em>Source: Their published rules (one author per strategy, named in the post). Full test: <a href="https://www.pastperformancelab.com/p/rsi2-orb-ut-bot-ttm-squeeze-backtest">Five Strategies, One Survivor</a>.</em></p><p>If you wrote one of these rules and think we got it wrong, write to pastperformancelab@protonmail.com. We print replies in full.</p><div class="subscription-widget-wrap-editor" data-attrs="{&quot;url&quot;:&quot;https://www.pastperformancelab.com/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe&quot;,&quot;language&quot;:&quot;en&quot;}" data-component-name="SubscribeWidgetToDOM"><div class="subscription-widget show-subscribe"><div class="preamble"><p class="cta-caption">One strategy tested every Tuesday. Free.</p></div><form class="subscription-widget-subscribe"><input type="email" class="email-input" name="email" placeholder="Type your email&#8230;" tabindex="-1"><input type="submit" class="button primary" value="Subscribe"><div class="fake-input-wrapper"><div class="fake-input"></div><div class="fake-button"></div></div></form></div></div><h3>Your turn</h3><p>Send us the strategy you are about to risk money on. Write to pastperformancelab@protonmail.com.</p><div><hr></div><p>Full method: <a href="https://www.pastperformancelab.com/p/how-we-backtest-trading-strategies">How We Test a Trading Strategy</a>.</p><p><em>Past performance is no guarantee of future results. We check anyway.</em></p><p><em>This is research on historical data, not investment advice. <a href="https://www.pastperformancelab.com/about">Full disclaimer</a>.</em></p>]]></content:encoded></item><item><title><![CDATA[Four Dip-Buying Rules Out-Earned Leverage. Only Two Passed.]]></title><description><![CDATA[We wrote the pass rule before the test ran. On top of QQQ, all four rules earned more than steady borrowing; two fell deeper than it did.]]></description><link>https://www.pastperformancelab.com/p/buy-the-dip-strategy-backtest-leverage</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/buy-the-dip-strategy-backtest-leverage</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Sun, 15 Nov 2026 12:18:50 GMT</pubDate><enclosure url="https://substackcdn.com/image/fetch/$s_!PiYg!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F48ead015-a8d8-46bb-8e5b-82b0c7eb9fe4_1280x1120.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Issue 13 &#183; November 2026 &#183; 4 dip-buying rules &#183; 1 pass rule, written first &#183; QQQ 2013&#8211;2026</em></p><p>Since 2013, each of these four rules trailed QQQ when it replaced QQQ. Added on top of QQQ, all four earned more. The top-up holds QQQ in full and borrows to double it on signal days.</p><p>The risk is plain leverage, which wins whenever the market outruns borrowing costs. So we first wrote down a win: more return than QQQ, more than steady leverage, and no deeper worst fall than steady leverage.</p><p>We wrote the pass rule on 28 October, before the test ran, and report it unchanged.</p><p><strong>Verdict: mixed, 2 of 4 rules pass. Should you use one? Not instead of QQQ. As an add-on, the test shows more return and deeper falls: every one fell further than QQQ.</strong><br><em>QQQ with dividends, 9 Jan 2013 &#8211; 30 Sep 2026, buy at the next open, borrowing at the US short-term government (T-bill) rate plus 1.5 points, 0.02% per buy or sell.</em></p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!PiYg!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F48ead015-a8d8-46bb-8e5b-82b0c7eb9fe4_1280x1120.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!PiYg!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F48ead015-a8d8-46bb-8e5b-82b0c7eb9fe4_1280x1120.png 424w, https://substackcdn.com/image/fetch/$s_!PiYg!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F48ead015-a8d8-46bb-8e5b-82b0c7eb9fe4_1280x1120.png 848w, https://substackcdn.com/image/fetch/$s_!PiYg!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F48ead015-a8d8-46bb-8e5b-82b0c7eb9fe4_1280x1120.png 1272w, https://substackcdn.com/image/fetch/$s_!PiYg!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F48ead015-a8d8-46bb-8e5b-82b0c7eb9fe4_1280x1120.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!PiYg!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F48ead015-a8d8-46bb-8e5b-82b0c7eb9fe4_1280x1120.png" width="1280" height="1120" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/48ead015-a8d8-46bb-8e5b-82b0c7eb9fe4_1280x1120.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1120,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:53988,&quot;alt&quot;:&quot;Table: all 4 top-ups out-earned QQQ (20% a year) and steady leverage; KAMA and Connors RSI(2) pass, Williams %R and Triple RSI fail only because their worst falls were deeper than steady leverage&#8217;s.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: all 4 top-ups out-earned QQQ (20% a year) and steady leverage; KAMA and Connors RSI(2) pass, Williams %R and Triple RSI fail only because their worst falls were deeper than steady leverage&#8217;s." title="Table: all 4 top-ups out-earned QQQ (20% a year) and steady leverage; KAMA and Connors RSI(2) pass, Williams %R and Triple RSI fail only because their worst falls were deeper than steady leverage&#8217;s." srcset="https://substackcdn.com/image/fetch/$s_!PiYg!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F48ead015-a8d8-46bb-8e5b-82b0c7eb9fe4_1280x1120.png 424w, https://substackcdn.com/image/fetch/$s_!PiYg!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F48ead015-a8d8-46bb-8e5b-82b0c7eb9fe4_1280x1120.png 848w, https://substackcdn.com/image/fetch/$s_!PiYg!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F48ead015-a8d8-46bb-8e5b-82b0c7eb9fe4_1280x1120.png 1272w, https://substackcdn.com/image/fetch/$s_!PiYg!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F48ead015-a8d8-46bb-8e5b-82b0c7eb9fe4_1280x1120.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><h3>Three checks before you trust a &#8220;beats buy-and-hold&#8221; claim</h3><ol><li><p><strong>Compare it with steady leverage.</strong> For example, a rule that borrows on a quarter of days must beat borrowing a quarter extra every day.</p></li><li><p><strong>Test the price you can actually get.</strong> Buying at the close means an order sent minutes before the bell. If you trade the next morning, test the next open.</p></li><li><p><strong>Write the pass rule first.</strong> Then report the result, even when a rule misses by half a point.</p></li></ol><p>01 / THE TEST</p><h2>Four dip-buying rules, one fair opponent</h2><p>Williams %R comes from <a href="https://quantifiedstrategies.substack.com/p/williams-r-trading-strategy-williams-203">Quantified Strategies</a>; we used its first exit (a close above the prior day&#8217;s high) and a 2-day lookback, the shortest it tested. KAMA (an adaptive moving average) mean reversion comes from a <a href="https://www.youtube.com/watch?v=lF_D0WZNBgc">Quantified Strategies video</a>; Kaufman&#8217;s default 2 and 30 settings are our assumption.</p><p>Triple RSI comes from <a href="https://quantifiedstrategies.substack.com/p/triple-rsi-trading-strategy-enhance">Quantified Strategies</a> too (our <a href="https://www.pastperformancelab.com/p/triple-rsi-strategy-backtest">Issue 10</a>). Connors RSI(2) is from Larry Connors and Cesar Alvarez&#8217;s <em>Short Term Trading Strategies That Work</em> (our <a href="https://www.pastperformancelab.com/p/connors-rsi-2-backtest-vs-buy-and-hold">Issue 05</a>).</p><p>The opponent, steady leverage, borrows the same average amount every day.</p><p>We charged the T-bill rate plus 1.5 points, close to the cheapest retail margin rates; most brokers charge more. Every trade fills at the next open, a price you can get with a day job.</p><p>02 / WHAT REPLICATED</p><h2>All four beat QQQ and steady leverage on return</h2><p>Every top-up beat QQQ alone, and beat steady leverage by 1.7 to 6.6 points a year.</p><p>In this historical test, from January 2013 to September 2026, QQQ alone turned $10,000 into about $124,000.</p><p>The top-ups ranged from about $166,000 (Triple RSI) to $471,000 (KAMA). Steady leverage with KAMA&#8217;s borrowing made about $234,000.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!azjF!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd0723d-a2a7-466d-bf96-7653dc53a24e_1280x982.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!azjF!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd0723d-a2a7-466d-bf96-7653dc53a24e_1280x982.png 424w, https://substackcdn.com/image/fetch/$s_!azjF!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd0723d-a2a7-466d-bf96-7653dc53a24e_1280x982.png 848w, https://substackcdn.com/image/fetch/$s_!azjF!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd0723d-a2a7-466d-bf96-7653dc53a24e_1280x982.png 1272w, https://substackcdn.com/image/fetch/$s_!azjF!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd0723d-a2a7-466d-bf96-7653dc53a24e_1280x982.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!azjF!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd0723d-a2a7-466d-bf96-7653dc53a24e_1280x982.png" width="1280" height="982" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/6bd0723d-a2a7-466d-bf96-7653dc53a24e_1280x982.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:982,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:42724,&quot;alt&quot;:&quot;Table: what $10,000 became from 9 Jan 2013 to 30 Sep 2026. QQQ alone about $124,000; top-ups from about $166,000 (Triple RSI) to $471,000 (KAMA); steady leverage with KAMA&#8217;s borrowing about $234,000. Hypothetical, past data.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: what $10,000 became from 9 Jan 2013 to 30 Sep 2026. QQQ alone about $124,000; top-ups from about $166,000 (Triple RSI) to $471,000 (KAMA); steady leverage with KAMA&#8217;s borrowing about $234,000. Hypothetical, past data." title="Table: what $10,000 became from 9 Jan 2013 to 30 Sep 2026. QQQ alone about $124,000; top-ups from about $166,000 (Triple RSI) to $471,000 (KAMA); steady leverage with KAMA&#8217;s borrowing about $234,000. Hypothetical, past data." srcset="https://substackcdn.com/image/fetch/$s_!azjF!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd0723d-a2a7-466d-bf96-7653dc53a24e_1280x982.png 424w, https://substackcdn.com/image/fetch/$s_!azjF!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd0723d-a2a7-466d-bf96-7653dc53a24e_1280x982.png 848w, https://substackcdn.com/image/fetch/$s_!azjF!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd0723d-a2a7-466d-bf96-7653dc53a24e_1280x982.png 1272w, https://substackcdn.com/image/fetch/$s_!azjF!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd0723d-a2a7-466d-bf96-7653dc53a24e_1280x982.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p>If you already hold QQQ, that is the news: on these dates, the dip signal earned more than borrowing alone.</p><p>03 / WHAT SPLIT THEM</p><h2>The worst falls decided it, by about a point or less</h2><p>The worst fall is the biggest drop from a peak to a later low. The last test: a top-up&#8217;s worst fall could be no deeper than steady leverage&#8217;s. KAMA and Connors RSI(2) cleared it. Williams %R missed by 1.1 points, Triple RSI by 0.5.</p><p>Williams %R&#8217;s edge needs a buy at the close, not the next morning (box below).</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!ELP7!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F947938d3-757e-41a4-ba41-064c0467aa29_1280x1028.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!ELP7!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F947938d3-757e-41a4-ba41-064c0467aa29_1280x1028.png 424w, https://substackcdn.com/image/fetch/$s_!ELP7!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F947938d3-757e-41a4-ba41-064c0467aa29_1280x1028.png 848w, https://substackcdn.com/image/fetch/$s_!ELP7!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F947938d3-757e-41a4-ba41-064c0467aa29_1280x1028.png 1272w, https://substackcdn.com/image/fetch/$s_!ELP7!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F947938d3-757e-41a4-ba41-064c0467aa29_1280x1028.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!ELP7!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F947938d3-757e-41a4-ba41-064c0467aa29_1280x1028.png" width="1280" height="1028" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/947938d3-757e-41a4-ba41-064c0467aa29_1280x1028.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1028,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:35810,&quot;alt&quot;:&quot;Chart: worst fall of each top-up against steady leverage. KAMA 1.60 points and Connors RSI(2) 1.87 points shallower; Williams %R 1.08 points and Triple RSI 0.48 points deeper.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Chart: worst fall of each top-up against steady leverage. KAMA 1.60 points and Connors RSI(2) 1.87 points shallower; Williams %R 1.08 points and Triple RSI 0.48 points deeper." title="Chart: worst fall of each top-up against steady leverage. KAMA 1.60 points and Connors RSI(2) 1.87 points shallower; Williams %R 1.08 points and Triple RSI 0.48 points deeper." srcset="https://substackcdn.com/image/fetch/$s_!ELP7!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F947938d3-757e-41a4-ba41-064c0467aa29_1280x1028.png 424w, https://substackcdn.com/image/fetch/$s_!ELP7!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F947938d3-757e-41a4-ba41-064c0467aa29_1280x1028.png 848w, https://substackcdn.com/image/fetch/$s_!ELP7!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F947938d3-757e-41a4-ba41-064c0467aa29_1280x1028.png 1272w, https://substackcdn.com/image/fetch/$s_!ELP7!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F947938d3-757e-41a4-ba41-064c0467aa29_1280x1028.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p>Every top-up fell further than QQQ&#8217;s own worst drop of 35%. If a fall like that would make you sell, skip these rules.</p><h3>How you trade it matters (reported only)</h3><p>These checks decide nothing.</p><ul><li><p><strong>Williams %R needs a buy at the closing price.</strong> Signalled at 15:50 New York time and bought at the close, it earned 32% a year to 31 Aug 2026; at the next open, 29%.</p></li><li><p><strong>KAMA is the reverse.</strong> It earned 32% at the next open and 30% with the 15:50 signal.</p></li><li><p><strong>No margin account?</strong> Without a margin account, the same signals can swap QQQ for QLD, a fund that moves twice QQQ&#8217;s daily change. It cost a fraction of a point to under two points a year against borrowing.</p></li></ul><p>04 / SHOULD YOU USE IT</p><h2>At most an add-on, and only if deeper falls would not shake you</h2><p>Run alone, none of these four rules beat QQQ since 2013. As top-ups, two passed and two narrowly failed. All of them borrow, and borrowing deepens the bad years. The question is whether you could hold through one.</p><div class="subscription-widget-wrap-editor" data-attrs="{&quot;url&quot;:&quot;https://www.pastperformancelab.com/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe&quot;,&quot;language&quot;:&quot;en&quot;}" data-component-name="SubscribeWidgetToDOM"><div class="subscription-widget show-subscribe"><div class="preamble"><p class="cta-caption">One strategy tested every Tuesday. Free.</p></div><form class="subscription-widget-subscribe"><input type="email" class="email-input" name="email" placeholder="Type your email&#8230;" tabindex="-1"><input type="submit" class="button primary" value="Subscribe"><div class="fake-input-wrapper"><div class="fake-input"></div><div class="fake-button"></div></div></form></div></div><h3>Your turn</h3><p>Send us the strategy you are about to risk money on. Reply to this email or write to pastperformancelab@protonmail.com.</p><div><hr></div><h3>Method</h3><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!Gf2b!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F61080cce-eaea-4f98-851a-fea55cda6a6f_1280x3112.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!Gf2b!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F61080cce-eaea-4f98-851a-fea55cda6a6f_1280x3112.png 424w, https://substackcdn.com/image/fetch/$s_!Gf2b!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F61080cce-eaea-4f98-851a-fea55cda6a6f_1280x3112.png 848w, https://substackcdn.com/image/fetch/$s_!Gf2b!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F61080cce-eaea-4f98-851a-fea55cda6a6f_1280x3112.png 1272w, https://substackcdn.com/image/fetch/$s_!Gf2b!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F61080cce-eaea-4f98-851a-fea55cda6a6f_1280x3112.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!Gf2b!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F61080cce-eaea-4f98-851a-fea55cda6a6f_1280x3112.png" width="1280" height="3112" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/61080cce-eaea-4f98-851a-fea55cda6a6f_1280x3112.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:3112,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:141273,&quot;alt&quot;:&quot;Table: full results for the 4 rules on QQQ, 9 Jan 2013 to 30 Sep 2026: the primary rows decide; close-fill, 15:50-signal, QLD-switch, SPY and combined rows are reported only and do not count.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: full results for the 4 rules on QQQ, 9 Jan 2013 to 30 Sep 2026: the primary rows decide; close-fill, 15:50-signal, QLD-switch, SPY and combined rows are reported only and do not count." title="Table: full results for the 4 rules on QQQ, 9 Jan 2013 to 30 Sep 2026: the primary rows decide; close-fill, 15:50-signal, QLD-switch, SPY and combined rows are reported only and do not count." srcset="https://substackcdn.com/image/fetch/$s_!Gf2b!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F61080cce-eaea-4f98-851a-fea55cda6a6f_1280x3112.png 424w, https://substackcdn.com/image/fetch/$s_!Gf2b!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F61080cce-eaea-4f98-851a-fea55cda6a6f_1280x3112.png 848w, https://substackcdn.com/image/fetch/$s_!Gf2b!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F61080cce-eaea-4f98-851a-fea55cda6a6f_1280x3112.png 1272w, https://substackcdn.com/image/fetch/$s_!Gf2b!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F61080cce-eaea-4f98-851a-fea55cda6a6f_1280x3112.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><ul><li><p><strong>Pass rule, written 28 Oct 2026.</strong> Beat QQQ and steady leverage on annual return, with a worst fall no deeper than steady leverage&#8217;s. The family holds at 3&#8211;4 passes, is mixed at 2 and fails at 0&#8211;1.</p></li><li><p><strong>Steady leverage</strong> holds 1 + E times QQQ daily, where E is the share of sessions with the top-up on. It borrows at the same rate. It pays no trading costs, which favours it.</p></li><li><p><strong>Rules, frozen as first tested.</strong> Williams %R(2) below &#8722;90, exit on a close above the prior day&#8217;s high; KAMA(5, 2, 30) mean reversion; Triple RSI as in Issue 10; Connors RSI(2) as in Issue 05.</p></li><li><p><strong>Data.</strong> Total-return prices frozen 7 Oct 2026, NYSE sessions, daily T-bill cash, annual returns by elapsed years.</p></li><li><p>The rules&#8217; authors are welcome to reply; we will publish any answer in full.</p></li></ul><p>Full method: <a href="https://www.pastperformancelab.com/p/how-we-backtest-trading-strategies">How We Test a Trading Strategy</a>.</p><p><em>Past performance is no guarantee of future results. We check anyway.</em></p><p><em>This is research on historical data, not investment advice. <a href="https://www.pastperformancelab.com/about">Full disclaimer</a>.</em></p>]]></content:encoded></item><item><title><![CDATA[The 8/21 Pullback, a Sixth of the Money]]></title><description><![CDATA[We rebuilt the 8/21 EMA first-pullback setup on 33 years of SPY. It roughly halves the worst fall, and ends far behind simply holding.]]></description><link>https://www.pastperformancelab.com/p/8-21-ema-crossover-strategy-backtest</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/8-21-ema-crossover-strategy-backtest</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Sat, 24 Oct 2026 13:22:58 GMT</pubDate><enclosure url="https://substackcdn.com/image/fetch/$s_!vUAR!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F21ff11bb-3ba6-47c3-aa8a-dff59dcae773_1280x1022.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Issue 11 &#183; October 2026 &#183; 182 SPY trades, 142 QQQ trades, 33 years</em></p><p>Two moving averages cross, price dips back, and you buy the first pullback. Justin Banks calls the 8/21 EMA setup the strategy that "<a href="https://x.com/RealJGBanks/status/2082265013948133722">will help you retire</a>", and it is a widely shared swing-trading rule.</p><p>It is also simple enough to test exactly. So we did: every bullish 8/21 cross on SPY since 1993 and on QQQ since 1999, and the first pullback after each one when there is one (182 of 193 SPY crosses, 142 of 158 on QQQ), costs included, cash earning T-bill interest while out.</p><p><strong>Verdict: trails the index.</strong><br><em>8/21 EMA cross, buy the first touch of the 8-day EMA, sell on the opposite cross &#183; SPY 1993&#8211;2026 and QQQ 1999&#8211;2026 &#183; 2 bp a side &#183; against buy-and-hold.</em></p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!vUAR!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F21ff11bb-3ba6-47c3-aa8a-dff59dcae773_1280x1022.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!vUAR!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F21ff11bb-3ba6-47c3-aa8a-dff59dcae773_1280x1022.png 424w, https://substackcdn.com/image/fetch/$s_!vUAR!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F21ff11bb-3ba6-47c3-aa8a-dff59dcae773_1280x1022.png 848w, https://substackcdn.com/image/fetch/$s_!vUAR!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F21ff11bb-3ba6-47c3-aa8a-dff59dcae773_1280x1022.png 1272w, https://substackcdn.com/image/fetch/$s_!vUAR!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F21ff11bb-3ba6-47c3-aa8a-dff59dcae773_1280x1022.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!vUAR!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F21ff11bb-3ba6-47c3-aa8a-dff59dcae773_1280x1022.png" width="1280" height="1022" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/21ff11bb-3ba6-47c3-aa8a-dff59dcae773_1280x1022.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1022,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:43644,&quot;alt&quot;:&quot;Table: $10,000 in the 8/21 rule on SPY became $49,923, against $316,014 for holding SPY; on QQQ $60,501 against $167,199. Return a year 4.93% vs 10.88% (SPY) and 6.81% vs 10.86% (QQQ). Worst fall &#8722;29.4% vs &#8722;55.2% and &#8722;28.6% vs &#8722;83.0%. In the market 54.8% and 53.6% of days; 37.4% of 182 and 36.6% of 142 trades won.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: $10,000 in the 8/21 rule on SPY became $49,923, against $316,014 for holding SPY; on QQQ $60,501 against $167,199. Return a year 4.93% vs 10.88% (SPY) and 6.81% vs 10.86% (QQQ). Worst fall &#8722;29.4% vs &#8722;55.2% and &#8722;28.6% vs &#8722;83.0%. In the market 54.8% and 53.6% of days; 37.4% of 182 and 36.6% of 142 trades won." title="Table: $10,000 in the 8/21 rule on SPY became $49,923, against $316,014 for holding SPY; on QQQ $60,501 against $167,199. Return a year 4.93% vs 10.88% (SPY) and 6.81% vs 10.86% (QQQ). Worst fall &#8722;29.4% vs &#8722;55.2% and &#8722;28.6% vs &#8722;83.0%. In the market 54.8% and 53.6% of days; 37.4% of 182 and 36.6% of 142 trades won." srcset="https://substackcdn.com/image/fetch/$s_!vUAR!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F21ff11bb-3ba6-47c3-aa8a-dff59dcae773_1280x1022.png 424w, https://substackcdn.com/image/fetch/$s_!vUAR!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F21ff11bb-3ba6-47c3-aa8a-dff59dcae773_1280x1022.png 848w, https://substackcdn.com/image/fetch/$s_!vUAR!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F21ff11bb-3ba6-47c3-aa8a-dff59dcae773_1280x1022.png 1272w, https://substackcdn.com/image/fetch/$s_!vUAR!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F21ff11bb-3ba6-47c3-aa8a-dff59dcae773_1280x1022.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p><code>01 / WHAT REPLICATED</code></p><h2>The setup makes money, and it does dodge the worst falls</h2><p>Start with what is true. Each trade earns a little on average (t-statistic about two, borderline on QQQ): a thin edge, not a proven one. Winners run and losers are cut, so a strategy that wins only a little over one trade in three still ends ahead.</p><p>The drawdown claim holds too. On SPY the worst fall is about half of holding's; on QQQ about a third. If the only question is "does it keep me out of crashes?", the answer is mostly yes.</p><p><code>02 / WHAT DID NOT</code></p><h2>Out of the market half the time, it ends with a sixth of the money</h2><p>The cost of dodging is sitting out. The strategy is invested a little over half the days. Ten thousand dollars in SPY in 1993 ends with about a sixth of holding's money; on QQQ a little over a third.</p><p>It beat holding in 7 of 34 calendar years on SPY and 8 of 28 on QQQ (first and last years partial). Five of SPY's seven and six of QQQ's eight came in years the index fell; in 2002 and 2022 the strategy lost money too, just less.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!oaFd!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F82e01d84-4d2f-4be8-93b8-82afc0a4d208_1280x1110.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!oaFd!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F82e01d84-4d2f-4be8-93b8-82afc0a4d208_1280x1110.png 424w, https://substackcdn.com/image/fetch/$s_!oaFd!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F82e01d84-4d2f-4be8-93b8-82afc0a4d208_1280x1110.png 848w, https://substackcdn.com/image/fetch/$s_!oaFd!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F82e01d84-4d2f-4be8-93b8-82afc0a4d208_1280x1110.png 1272w, https://substackcdn.com/image/fetch/$s_!oaFd!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F82e01d84-4d2f-4be8-93b8-82afc0a4d208_1280x1110.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!oaFd!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F82e01d84-4d2f-4be8-93b8-82afc0a4d208_1280x1110.png" width="1280" height="1110" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/82e01d84-4d2f-4be8-93b8-82afc0a4d208_1280x1110.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1110,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:38437,&quot;alt&quot;:&quot;Table: years the rule beat holding. SPY 1994: rule 0.5%, hold 0.4%; SPY 2001: rule 1.5%, hold &#8722;11.8%; SPY 2002: rule &#8722;7.0%, hold &#8722;21.6%; SPY 2008: rule 1.0%, hold &#8722;36.8%; SPY 2018: rule &#8722;2.7%, hold &#8722;4.6%; SPY 2022: rule &#8722;7.6%, hold &#8722;18.2%; SPY 2025: rule 19.0%, hold 17.7%; QQQ 2000: rule 10.4%, hold &#8722;36.1%; QQQ 2001: rule 5.2%, hold &#8722;33.3%; QQQ 2002: rule &#8722;9.4%, hold &#8722;37.4%; QQQ 2006: rule 10.5%, hold 7.1%; QQQ 2008: rule 1.3%, hold &#8722;41.7%; QQQ 2018: rule 2.1%, hold &#8722;0.1%; QQQ 2022: rule &#8722;17.0%, hold &#8722;32.6%; QQQ 2025: rule 22.3%, hold 20.8%.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: years the rule beat holding. SPY 1994: rule 0.5%, hold 0.4%; SPY 2001: rule 1.5%, hold &#8722;11.8%; SPY 2002: rule &#8722;7.0%, hold &#8722;21.6%; SPY 2008: rule 1.0%, hold &#8722;36.8%; SPY 2018: rule &#8722;2.7%, hold &#8722;4.6%; SPY 2022: rule &#8722;7.6%, hold &#8722;18.2%; SPY 2025: rule 19.0%, hold 17.7%; QQQ 2000: rule 10.4%, hold &#8722;36.1%; QQQ 2001: rule 5.2%, hold &#8722;33.3%; QQQ 2002: rule &#8722;9.4%, hold &#8722;37.4%; QQQ 2006: rule 10.5%, hold 7.1%; QQQ 2008: rule 1.3%, hold &#8722;41.7%; QQQ 2018: rule 2.1%, hold &#8722;0.1%; QQQ 2022: rule &#8722;17.0%, hold &#8722;32.6%; QQQ 2025: rule 22.3%, hold 20.8%." title="Table: years the rule beat holding. SPY 1994: rule 0.5%, hold 0.4%; SPY 2001: rule 1.5%, hold &#8722;11.8%; SPY 2002: rule &#8722;7.0%, hold &#8722;21.6%; SPY 2008: rule 1.0%, hold &#8722;36.8%; SPY 2018: rule &#8722;2.7%, hold &#8722;4.6%; SPY 2022: rule &#8722;7.6%, hold &#8722;18.2%; SPY 2025: rule 19.0%, hold 17.7%; QQQ 2000: rule 10.4%, hold &#8722;36.1%; QQQ 2001: rule 5.2%, hold &#8722;33.3%; QQQ 2002: rule &#8722;9.4%, hold &#8722;37.4%; QQQ 2006: rule 10.5%, hold 7.1%; QQQ 2008: rule 1.3%, hold &#8722;41.7%; QQQ 2018: rule 2.1%, hold &#8722;0.1%; QQQ 2022: rule &#8722;17.0%, hold &#8722;32.6%; QQQ 2025: rule 22.3%, hold 20.8%." srcset="https://substackcdn.com/image/fetch/$s_!oaFd!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F82e01d84-4d2f-4be8-93b8-82afc0a4d208_1280x1110.png 424w, https://substackcdn.com/image/fetch/$s_!oaFd!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F82e01d84-4d2f-4be8-93b8-82afc0a4d208_1280x1110.png 848w, https://substackcdn.com/image/fetch/$s_!oaFd!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F82e01d84-4d2f-4be8-93b8-82afc0a4d208_1280x1110.png 1272w, https://substackcdn.com/image/fetch/$s_!oaFd!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F82e01d84-4d2f-4be8-93b8-82afc0a4d208_1280x1110.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p><code>03 / THE ONE WINDOW IT WINS</code></p><h2>QQQ 1999&#8211;2012: when stepping aside was the whole game</h2><p>There is one stretch where it won: QQQ from mid-1999 to 2012, through the dot-com crash and 2008. Holding earned about 2% a year in that stretch; the strategy more than doubled that. From 2013 on, holding QQQ ran away from it.</p><p>That is the honest shape of this rule. It is a crash filter with a large toll, and it pays off only in decades that crash hard and recover slowly, and even then only on QQQ, whose 2000&#8211;02 fall was deep enough; SPY trailed in the same years.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!7PE1!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcf44f748-4aa3-46b8-80ba-64acbf8c8fc7_1280x902.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!7PE1!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcf44f748-4aa3-46b8-80ba-64acbf8c8fc7_1280x902.png 424w, https://substackcdn.com/image/fetch/$s_!7PE1!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcf44f748-4aa3-46b8-80ba-64acbf8c8fc7_1280x902.png 848w, https://substackcdn.com/image/fetch/$s_!7PE1!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcf44f748-4aa3-46b8-80ba-64acbf8c8fc7_1280x902.png 1272w, https://substackcdn.com/image/fetch/$s_!7PE1!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcf44f748-4aa3-46b8-80ba-64acbf8c8fc7_1280x902.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!7PE1!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcf44f748-4aa3-46b8-80ba-64acbf8c8fc7_1280x902.png" width="1280" height="902" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/cf44f748-4aa3-46b8-80ba-64acbf8c8fc7_1280x902.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:902,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:28213,&quot;alt&quot;:&quot;Table: return a year, 8/21 rule vs holding. SPY 1993 to 2012: 4.30% vs 8.15%; SPY 2013 to 2026: 5.84% vs 14.92%; QQQ mid-1999 to 2012: 4.92% vs 2.04%; QQQ 2013 to 2026: 8.71% vs 20.33%.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: return a year, 8/21 rule vs holding. SPY 1993 to 2012: 4.30% vs 8.15%; SPY 2013 to 2026: 5.84% vs 14.92%; QQQ mid-1999 to 2012: 4.92% vs 2.04%; QQQ 2013 to 2026: 8.71% vs 20.33%." title="Table: return a year, 8/21 rule vs holding. SPY 1993 to 2012: 4.30% vs 8.15%; SPY 2013 to 2026: 5.84% vs 14.92%; QQQ mid-1999 to 2012: 4.92% vs 2.04%; QQQ 2013 to 2026: 8.71% vs 20.33%." srcset="https://substackcdn.com/image/fetch/$s_!7PE1!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcf44f748-4aa3-46b8-80ba-64acbf8c8fc7_1280x902.png 424w, https://substackcdn.com/image/fetch/$s_!7PE1!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcf44f748-4aa3-46b8-80ba-64acbf8c8fc7_1280x902.png 848w, https://substackcdn.com/image/fetch/$s_!7PE1!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcf44f748-4aa3-46b8-80ba-64acbf8c8fc7_1280x902.png 1272w, https://substackcdn.com/image/fetch/$s_!7PE1!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcf44f748-4aa3-46b8-80ba-64acbf8c8fc7_1280x902.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p><code>04 / IS 8/21 SPECIAL?</code></p><h2>No. Every nearby setting trails holding</h2><p>We moved the averages (5/13, 9/21, 10/30, 20/50), touched the slower average instead of the faster one, and tried costs from 0 to 10 bp a side. None of it beats holding. 8/21 is neither the best nor the worst: mid-table on SPY, second on QQQ. Not a lucky outlier, and not a magic pair either.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!QQ_N!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff869ed4e-1b41-4497-abb4-8ac8d55d4c72_1280x1296.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!QQ_N!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff869ed4e-1b41-4497-abb4-8ac8d55d4c72_1280x1296.png 424w, https://substackcdn.com/image/fetch/$s_!QQ_N!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff869ed4e-1b41-4497-abb4-8ac8d55d4c72_1280x1296.png 848w, https://substackcdn.com/image/fetch/$s_!QQ_N!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff869ed4e-1b41-4497-abb4-8ac8d55d4c72_1280x1296.png 1272w, https://substackcdn.com/image/fetch/$s_!QQ_N!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff869ed4e-1b41-4497-abb4-8ac8d55d4c72_1280x1296.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!QQ_N!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff869ed4e-1b41-4497-abb4-8ac8d55d4c72_1280x1296.png" width="1280" height="1296" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/f869ed4e-1b41-4497-abb4-8ac8d55d4c72_1280x1296.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1296,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:41845,&quot;alt&quot;:&quot;Table: return a year for nearby settings and costs. 5/13: SPY 2.88%, QQQ 4.97%; 8/21: SPY 4.93%, QQQ 6.81%; 9/21: SPY 4.44%, QQQ 6.78%; 10/30: SPY 5.05%, QQQ 7.95%; 20/50: SPY 7.18%, QQQ 4.70%; 8/21, touch the slow line: SPY 4.53%, QQQ 6.63%; 0 bp a side: SPY 5.16%, QQQ 7.03%; 5 bp a side: SPY 4.59%, QQQ 6.48%; 10 bp a side: SPY 4.02%, QQQ 5.93%; buy and hold: SPY 10.88%, QQQ 10.86%. None beats holding.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: return a year for nearby settings and costs. 5/13: SPY 2.88%, QQQ 4.97%; 8/21: SPY 4.93%, QQQ 6.81%; 9/21: SPY 4.44%, QQQ 6.78%; 10/30: SPY 5.05%, QQQ 7.95%; 20/50: SPY 7.18%, QQQ 4.70%; 8/21, touch the slow line: SPY 4.53%, QQQ 6.63%; 0 bp a side: SPY 5.16%, QQQ 7.03%; 5 bp a side: SPY 4.59%, QQQ 6.48%; 10 bp a side: SPY 4.02%, QQQ 5.93%; buy and hold: SPY 10.88%, QQQ 10.86%. None beats holding." title="Table: return a year for nearby settings and costs. 5/13: SPY 2.88%, QQQ 4.97%; 8/21: SPY 4.93%, QQQ 6.81%; 9/21: SPY 4.44%, QQQ 6.78%; 10/30: SPY 5.05%, QQQ 7.95%; 20/50: SPY 7.18%, QQQ 4.70%; 8/21, touch the slow line: SPY 4.53%, QQQ 6.63%; 0 bp a side: SPY 5.16%, QQQ 7.03%; 5 bp a side: SPY 4.59%, QQQ 6.48%; 10 bp a side: SPY 4.02%, QQQ 5.93%; buy and hold: SPY 10.88%, QQQ 10.86%. None beats holding." srcset="https://substackcdn.com/image/fetch/$s_!QQ_N!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff869ed4e-1b41-4497-abb4-8ac8d55d4c72_1280x1296.png 424w, https://substackcdn.com/image/fetch/$s_!QQ_N!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff869ed4e-1b41-4497-abb4-8ac8d55d4c72_1280x1296.png 848w, https://substackcdn.com/image/fetch/$s_!QQ_N!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff869ed4e-1b41-4497-abb4-8ac8d55d4c72_1280x1296.png 1272w, https://substackcdn.com/image/fetch/$s_!QQ_N!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff869ed4e-1b41-4497-abb4-8ac8d55d4c72_1280x1296.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><h3>The transferable part</h3><ol><li><p><strong>Count the days out.</strong> A rule that is invested half the time must earn nearly twice as much per day invested to keep up. Ask for exposure next to every win rate.</p></li><li><p><strong>Ask "against what?"</strong> A drawdown halved is only good news if the money at the end is close. Compare final dollars, not just the worst month.</p></li><li><p><strong>Find its one good window.</strong> Most timing rules have a stretch they win. Check whether the claim rests on it.</p></li></ol><div class="subscription-widget-wrap-editor" data-attrs="{&quot;url&quot;:&quot;https://www.pastperformancelab.com/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe&quot;,&quot;language&quot;:&quot;en&quot;}" data-component-name="SubscribeWidgetToDOM"><div class="subscription-widget show-subscribe"><div class="preamble"><p class="cta-caption">One strategy tested every Tuesday. Free.</p></div><form class="subscription-widget-subscribe"><input type="email" class="email-input" name="email" placeholder="Type your email&#8230;" tabindex="-1"><input type="submit" class="button primary" value="Subscribe"><div class="fake-input-wrapper"><div class="fake-input"></div><div class="fake-button"></div></div></form></div></div><h3>Your turn</h3><p>Send us the strategy you are about to risk money on. Reply to this email or write to pastperformancelab@protonmail.com. The first reader submission becomes Reader Test #1.</p><div><hr></div><h3>Method</h3><ul><li><p>Rules as published by <a href="https://x.com/RealJGBanks/status/2082265013948133722">Justin Banks on X</a>: the 8 EMA crosses above the 21 EMA, buy the first pullback. The post does not define the pullback or the exit, so we chose a touch of the 8-day EMA and an exit on the opposite cross, and show the 21-day touch too. We test the long side only.</p></li><li><p>Data: SPY and QQQ daily prices, raw and total-return adjusted, frozen to one file before the test (md5 <code>5efa8323eaa5d3fbfad614f949ec2693</code>, last session 30 Sep 2026). NYSE calendar.</p></li><li><p>Signals on raw closes; returns on total-return prices. EMA 8 and 21 (standard recursive EMA). Setup: EMA8 closes above EMA21 after being at or below it. Entry: the first later day in the setup whose low is at or below EMA8; buy at the next open; one entry per setup. Exit: the next open after EMA8 closes below EMA21. 60-session warm-up before the first signal.</p></li><li><p>Costs 2 bp a side (0, 5 and 10 bp shown). Cash earns the daily 4-week T-bill rate (FRED) when out. Annual returns by elapsed years.</p></li><li><p>Trade counts and win rates include one open trade per ETF, valued at 30 Sep.</p></li><li><p>Ties: no session had the two averages within 1e-6 of each other, so no result depends on a tie.</p></li><li><p>Windows: SPY 27 Apr 1993 &#8211; 30 Sep 2026; QQQ 4 Jun 1999 &#8211; 30 Sep 2026.</p></li></ul><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!Ap-A!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8f248047-56de-4987-bab2-8670120fdefb_1280x2110.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!Ap-A!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8f248047-56de-4987-bab2-8670120fdefb_1280x2110.png 424w, https://substackcdn.com/image/fetch/$s_!Ap-A!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8f248047-56de-4987-bab2-8670120fdefb_1280x2110.png 848w, https://substackcdn.com/image/fetch/$s_!Ap-A!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8f248047-56de-4987-bab2-8670120fdefb_1280x2110.png 1272w, https://substackcdn.com/image/fetch/$s_!Ap-A!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8f248047-56de-4987-bab2-8670120fdefb_1280x2110.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!Ap-A!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8f248047-56de-4987-bab2-8670120fdefb_1280x2110.png" width="1280" height="2110" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/8f248047-56de-4987-bab2-8670120fdefb_1280x2110.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:2110,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:75376,&quot;alt&quot;:&quot;Table: full results. Return a year: 4.93%, 10.88%, 6.81%, 10.86%; $10,000 becomes: $49,923, $316,014, $60,501, $167,199; Worst fall: &#8722;29.4%, &#8722;55.2%, &#8722;28.6%, &#8722;83.0%; Sharpe ratio over T-bills: 0.29, 0.52, 0.39, 0.45; Days in the market: 54.8%, 100%, 53.6%, 100%; Trades one open at 30 Sep: 182, not applicable, 142, not applicable; Winning trades: 37.4%, not applicable, 36.6%, not applicable; Average trade: 0.82%, not applicable, 1.42%, not applicable; Median trade: &#8722;0.79%, not applicable, &#8722;1.36%, not applicable; Profit factor: 1.71, not applicable, 1.81, not applicable; t-statistic trade returns vs zero: 2.19, not applicable, 1.94, not applicable; Best / worst trade: 32.8% / &#8722;10.0%, not applicable, 68.9% / &#8722;8.9%, not applicable; Average days held: 25.3, not applicable, 25.9, not applicable; Years beating hold: 7 of 34, not applicable, 8 of 28, not applicable; Losing years: 13, not applicable, 10, not applicable.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: full results. Return a year: 4.93%, 10.88%, 6.81%, 10.86%; $10,000 becomes: $49,923, $316,014, $60,501, $167,199; Worst fall: &#8722;29.4%, &#8722;55.2%, &#8722;28.6%, &#8722;83.0%; Sharpe ratio over T-bills: 0.29, 0.52, 0.39, 0.45; Days in the market: 54.8%, 100%, 53.6%, 100%; Trades one open at 30 Sep: 182, not applicable, 142, not applicable; Winning trades: 37.4%, not applicable, 36.6%, not applicable; Average trade: 0.82%, not applicable, 1.42%, not applicable; Median trade: &#8722;0.79%, not applicable, &#8722;1.36%, not applicable; Profit factor: 1.71, not applicable, 1.81, not applicable; t-statistic trade returns vs zero: 2.19, not applicable, 1.94, not applicable; Best / worst trade: 32.8% / &#8722;10.0%, not applicable, 68.9% / &#8722;8.9%, not applicable; Average days held: 25.3, not applicable, 25.9, not applicable; Years beating hold: 7 of 34, not applicable, 8 of 28, not applicable; Losing years: 13, not applicable, 10, not applicable." title="Table: full results. Return a year: 4.93%, 10.88%, 6.81%, 10.86%; $10,000 becomes: $49,923, $316,014, $60,501, $167,199; Worst fall: &#8722;29.4%, &#8722;55.2%, &#8722;28.6%, &#8722;83.0%; Sharpe ratio over T-bills: 0.29, 0.52, 0.39, 0.45; Days in the market: 54.8%, 100%, 53.6%, 100%; Trades one open at 30 Sep: 182, not applicable, 142, not applicable; Winning trades: 37.4%, not applicable, 36.6%, not applicable; Average trade: 0.82%, not applicable, 1.42%, not applicable; Median trade: &#8722;0.79%, not applicable, &#8722;1.36%, not applicable; Profit factor: 1.71, not applicable, 1.81, not applicable; t-statistic trade returns vs zero: 2.19, not applicable, 1.94, not applicable; Best / worst trade: 32.8% / &#8722;10.0%, not applicable, 68.9% / &#8722;8.9%, not applicable; Average days held: 25.3, not applicable, 25.9, not applicable; Years beating hold: 7 of 34, not applicable, 8 of 28, not applicable; Losing years: 13, not applicable, 10, not applicable." srcset="https://substackcdn.com/image/fetch/$s_!Ap-A!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8f248047-56de-4987-bab2-8670120fdefb_1280x2110.png 424w, https://substackcdn.com/image/fetch/$s_!Ap-A!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8f248047-56de-4987-bab2-8670120fdefb_1280x2110.png 848w, https://substackcdn.com/image/fetch/$s_!Ap-A!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8f248047-56de-4987-bab2-8670120fdefb_1280x2110.png 1272w, https://substackcdn.com/image/fetch/$s_!Ap-A!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8f248047-56de-4987-bab2-8670120fdefb_1280x2110.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p>Full method: <a href="https://www.pastperformancelab.com/p/how-we-backtest-trading-strategies">How We Test a Trading Strategy</a>.</p><p><em>Past performance is no guarantee of future results. We check anyway.</em></p><p><em>This is research on historical data, not investment advice. <a href="https://www.pastperformancelab.com/about">Full disclaimer</a>.</em></p>]]></content:encoded></item><item><title><![CDATA[Nine Wins in Ten, a Quarter of the Money]]></title><description><![CDATA[Triple RSI's 90% win rate on the S&P 500 is real. Then we counted the days it sits in cash.]]></description><link>https://www.pastperformancelab.com/p/triple-rsi-strategy-backtest</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/triple-rsi-strategy-backtest</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Tue, 20 Oct 2026 10:58:34 GMT</pubDate><enclosure url="https://substackcdn.com/image/fetch/$s_!Ay6z!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc738156c-07a0-4306-b214-4f5d4ee5afa7_1280x1058.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Issue 10 &#183; October 2026 &#183; 91 trades &#183; 33 years &#183; 18 settings &#183; 1 family test</em></p><p>Nine wins out of ten. That is the promise of Triple RSI, a dip-buying rule for the S&amp;P 500 <a href="https://quantifiedstrategies.substack.com/p/triple-rsi-trading-strategy-enhance">published by Quantified Strategies</a>. We expected the number to shrink once we ran it ourselves.</p><p>It did not shrink. The win rate came out at 90.1% across 91 trades since 1993. And an account that traded it still ended with less than a quarter of what a plain index holder made.</p><p><strong>Verdict: the claim is true, the strategy trails the index badly on its own, and it earns its keep only as a top-up on an index position.</strong><br><em>SPY total return, 11 Nov 1993 &#8211; 22 Sep 2026, NYSE sessions, a 0.02% cost per trade side, cash in T-bills when flat.</em></p><blockquote><p><strong>The 60-second verdict</strong></p><ul><li><p><strong>What it claims.</strong> Buy the S&amp;P 500 fund after a three-day slide in a short-term momentum gauge, while the long-term trend is up. Sell on the bounce. Win about 90% of the time.</p></li><li><p><strong>What we found.</strong> The 90% is real: 82 winners in 91 trades. But the rule trades about three times a year and sits in cash 95% of the time.</p></li><li><p><strong>The $10,000 test (Nov 1993 &#8211; Sep 2026).</strong> The strategy turned $10,000 into about $70,500. Just holding the index fund turned it into about $298,000. Holding the fund and doubling up on signal days made about $870,000, using borrowed money.</p></li><li><p><strong>Should you use it?</strong> Not on its own. Only as an add-on to an index position you already hold, and only if you can carry double exposure on bad days.</p></li></ul></blockquote><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!Ay6z!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc738156c-07a0-4306-b214-4f5d4ee5afa7_1280x1058.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!Ay6z!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc738156c-07a0-4306-b214-4f5d4ee5afa7_1280x1058.png 424w, https://substackcdn.com/image/fetch/$s_!Ay6z!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc738156c-07a0-4306-b214-4f5d4ee5afa7_1280x1058.png 848w, https://substackcdn.com/image/fetch/$s_!Ay6z!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc738156c-07a0-4306-b214-4f5d4ee5afa7_1280x1058.png 1272w, https://substackcdn.com/image/fetch/$s_!Ay6z!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc738156c-07a0-4306-b214-4f5d4ee5afa7_1280x1058.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!Ay6z!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc738156c-07a0-4306-b214-4f5d4ee5afa7_1280x1058.png" width="1280" height="1058" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/c738156c-07a0-4306-b214-4f5d4ee5afa7_1280x1058.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1058,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:41670,&quot;alt&quot;:&quot;Table: $10,000 invested from 11 Nov 1993 to 22 Sep 2026. Triple RSI alone became $70,541, SPY bought and held $298,391, and SPY plus a second SPY position on signal days $870,448. Return a year: 6.13%, 10.89% and 14.56%. Worst fall: &#8722;13.8%, &#8722;55.2% and &#8722;55.2%. Triple RSI was in the market on 5.2% of 8,270 sessions and won 82 of 91 trades (90.1%).&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: $10,000 invested from 11 Nov 1993 to 22 Sep 2026. Triple RSI alone became $70,541, SPY bought and held $298,391, and SPY plus a second SPY position on signal days $870,448. Return a year: 6.13%, 10.89% and 14.56%. Worst fall: &#8722;13.8%, &#8722;55.2% and &#8722;55.2%. Triple RSI was in the market on 5.2% of 8,270 sessions and won 82 of 91 trades (90.1%)." title="Table: $10,000 invested from 11 Nov 1993 to 22 Sep 2026. Triple RSI alone became $70,541, SPY bought and held $298,391, and SPY plus a second SPY position on signal days $870,448. Return a year: 6.13%, 10.89% and 14.56%. Worst fall: &#8722;13.8%, &#8722;55.2% and &#8722;55.2%. Triple RSI was in the market on 5.2% of 8,270 sessions and won 82 of 91 trades (90.1%)." srcset="https://substackcdn.com/image/fetch/$s_!Ay6z!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc738156c-07a0-4306-b214-4f5d4ee5afa7_1280x1058.png 424w, https://substackcdn.com/image/fetch/$s_!Ay6z!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc738156c-07a0-4306-b214-4f5d4ee5afa7_1280x1058.png 848w, https://substackcdn.com/image/fetch/$s_!Ay6z!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc738156c-07a0-4306-b214-4f5d4ee5afa7_1280x1058.png 1272w, https://substackcdn.com/image/fetch/$s_!Ay6z!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc738156c-07a0-4306-b214-4f5d4ee5afa7_1280x1058.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p><code>01 / THE CLAIM</code></p><h2>The 90% reproduces</h2><p>RSI is a 0-to-100 gauge of how hard a price has fallen or risen lately. Triple RSI buys SPY at the close when the five-day RSI is below 30 and has fallen three days running. It also needs RSI below 60 three days earlier and a price above its 200-day average. It sells when RSI climbs back above 50.</p><p>We ran it on SPY with dividends, on real exchange sessions, with a small cost on every trade. <a href="https://quantifiedstrategies.substack.com/p/triple-rsi-trading-strategy-elevate-a14">The source reports</a> 83 trades and a 1.4% average gain. With data to September 2026 we count 91 trades and 1.35%, and 90.1% of them won. The average trade lasted under five trading days.</p><p>Then we tried to break it. The published setting and 17 nearby variations all won between 82% and 92% of their trades. Doubling the costs moved the yearly return from 6.1% to 6.0%. If you saw this win rate in a screenshot, you saw the truth.</p><p><code>02 / THE CATCH</code></p><h2>A win rate is not a return</h2><p>Here is what the screenshot leaves out. The rule fires about three times a year and holds for about five trading days. So your money is in the market one day in twenty.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!Fodt!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4b19cae0-b3e6-4ffb-b7df-6df85e07ae16_1280x752.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!Fodt!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4b19cae0-b3e6-4ffb-b7df-6df85e07ae16_1280x752.png 424w, https://substackcdn.com/image/fetch/$s_!Fodt!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4b19cae0-b3e6-4ffb-b7df-6df85e07ae16_1280x752.png 848w, https://substackcdn.com/image/fetch/$s_!Fodt!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4b19cae0-b3e6-4ffb-b7df-6df85e07ae16_1280x752.png 1272w, https://substackcdn.com/image/fetch/$s_!Fodt!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4b19cae0-b3e6-4ffb-b7df-6df85e07ae16_1280x752.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!Fodt!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4b19cae0-b3e6-4ffb-b7df-6df85e07ae16_1280x752.png" width="1280" height="752" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/4b19cae0-b3e6-4ffb-b7df-6df85e07ae16_1280x752.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:752,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:24305,&quot;alt&quot;:&quot;Two strips. The first splits 8,270 NYSE sessions from 11 Nov 1993 to 22 Sep 2026: Triple RSI held SPY on 426 of them (5.2%) and sat in T-bills on 7,844 (94.8%). The second is a timeline with a thin blue mark for each of its 91 trades, spread thinly from 1993 to 2026, with long gaps.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Two strips. The first splits 8,270 NYSE sessions from 11 Nov 1993 to 22 Sep 2026: Triple RSI held SPY on 426 of them (5.2%) and sat in T-bills on 7,844 (94.8%). The second is a timeline with a thin blue mark for each of its 91 trades, spread thinly from 1993 to 2026, with long gaps." title="Two strips. The first splits 8,270 NYSE sessions from 11 Nov 1993 to 22 Sep 2026: Triple RSI held SPY on 426 of them (5.2%) and sat in T-bills on 7,844 (94.8%). The second is a timeline with a thin blue mark for each of its 91 trades, spread thinly from 1993 to 2026, with long gaps." srcset="https://substackcdn.com/image/fetch/$s_!Fodt!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4b19cae0-b3e6-4ffb-b7df-6df85e07ae16_1280x752.png 424w, https://substackcdn.com/image/fetch/$s_!Fodt!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4b19cae0-b3e6-4ffb-b7df-6df85e07ae16_1280x752.png 848w, https://substackcdn.com/image/fetch/$s_!Fodt!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4b19cae0-b3e6-4ffb-b7df-6df85e07ae16_1280x752.png 1272w, https://substackcdn.com/image/fetch/$s_!Fodt!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4b19cae0-b3e6-4ffb-b7df-6df85e07ae16_1280x752.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p>The other nineteen days it earns the T-bill rate. Add it up and the account grows 6.1% a year. SPY, held and ignored, grew 10.9%.</p><p>That gap compounds. Over almost 33 years it is the difference between $70,500 and $298,000. You win nearly every trade and still finish far behind someone who never traded.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!y-9o!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F55afb8e8-b30b-45b2-a19d-e5164d3cf242_1280x1082.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!y-9o!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F55afb8e8-b30b-45b2-a19d-e5164d3cf242_1280x1082.png 424w, https://substackcdn.com/image/fetch/$s_!y-9o!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F55afb8e8-b30b-45b2-a19d-e5164d3cf242_1280x1082.png 848w, https://substackcdn.com/image/fetch/$s_!y-9o!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F55afb8e8-b30b-45b2-a19d-e5164d3cf242_1280x1082.png 1272w, https://substackcdn.com/image/fetch/$s_!y-9o!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F55afb8e8-b30b-45b2-a19d-e5164d3cf242_1280x1082.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!y-9o!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F55afb8e8-b30b-45b2-a19d-e5164d3cf242_1280x1082.png" width="1280" height="1082" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/55afb8e8-b30b-45b2-a19d-e5164d3cf242_1280x1082.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1082,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:46007,&quot;alt&quot;:&quot;Line chart on a log scale, 1993 to 2026: growth of $10,000. Triple RSI alone ends at $70,541, SPY bought and held at $298,391, and SPY plus a second SPY position on signal days at $870,448. The Triple RSI line rises slowly and steadily and stays far below the other two, which move together and both fall hard in 2000&#8211;02 and 2008.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Line chart on a log scale, 1993 to 2026: growth of $10,000. Triple RSI alone ends at $70,541, SPY bought and held at $298,391, and SPY plus a second SPY position on signal days at $870,448. The Triple RSI line rises slowly and steadily and stays far below the other two, which move together and both fall hard in 2000&#8211;02 and 2008." title="Line chart on a log scale, 1993 to 2026: growth of $10,000. Triple RSI alone ends at $70,541, SPY bought and held at $298,391, and SPY plus a second SPY position on signal days at $870,448. The Triple RSI line rises slowly and steadily and stays far below the other two, which move together and both fall hard in 2000&#8211;02 and 2008." srcset="https://substackcdn.com/image/fetch/$s_!y-9o!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F55afb8e8-b30b-45b2-a19d-e5164d3cf242_1280x1082.png 424w, https://substackcdn.com/image/fetch/$s_!y-9o!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F55afb8e8-b30b-45b2-a19d-e5164d3cf242_1280x1082.png 848w, https://substackcdn.com/image/fetch/$s_!y-9o!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F55afb8e8-b30b-45b2-a19d-e5164d3cf242_1280x1082.png 1272w, https://substackcdn.com/image/fetch/$s_!y-9o!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F55afb8e8-b30b-45b2-a19d-e5164d3cf242_1280x1082.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p>There is one real consolation. The strategy's worst fall was 14%, against 55% for the index. If you could not sit through a halving, that matters. You pay for the comfort with three quarters of the final wealth.</p><p><code>03 / THE USE</code></p><h2>It works as a top-up, not as a strategy</h2><p>So is the signal useless? No. Ask a different question. What if you hold SPY anyway and add a second position only on signal days?</p><p>That version grew 14.6% a year against 10.9%. It beat plain SPY in 27 of 34 calendar years. This is the shape we keep finding: a rule that is weak alone can be <a href="https://www.pastperformancelab.com/p/opening-range-breakout-backtest-gap-filter">a useful sidekick to the index</a>.</p><p>Three warnings before you copy it. The top-up is borrowed money, so you need margin or futures. It does nothing in a crash: the worst fall is the same 55%.</p><p>And the edge has thinned. Since 2020 the win rate is 81%. The top-up still added about two and a half points a year over that stretch, but it trailed plain SPY in 2025 and so far in 2026.</p><p><code>04 / THE BAR</code></p><h2>Against the Nasdaq, it is closer than it looks</h2><p>Our bar is the Nasdaq 100 fund, QQQ. SPY is only the floor. Run the same rules on QQQ and the win rate drops to 82% across 76 trades. The top-up still helps there: 12.0% a year against 9.2% for plain QQQ since December 1999.</p><p>Now look at the years when the Nasdaq ran. From 2013 to August 2026, SPY plus the top-up grew 18.5% a year. Plain QQQ grew 20.2%. If you held the Nasdaq through those years, this signal on SPY would not have beaten you. Since December 1999 as a whole, it would have: 11.4% a year against 9.0%.</p><h3>Same family: the ATR coil breakout</h3><p>A cousin of dip-buying is the volatility breakout. One version, from Breakout Trading Academy, buys the Nasdaq 100 when price jumps 2.5 "average ranges" above a bar's open. It trades only after a quiet spell, the "coil". We read the rules from partial captures, so this is our reading; if the academy shares the exact rules, we will rerun it.</p><p>We tested six versions on one-minute index data from 2013 to August 2026. Every one beat cash, and none by much. The best grew 3.4% a year, against 1.7% for T-bills and 20.2% for QQQ.</p><p>The coil added almost nothing to the account. The same breakout with no quiet-spell filter grew 3.3% a year. When you can delete a rule's key idea and keep the result, you are not buying that idea.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!I34K!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8e90f393-01d3-418a-b297-c5ff95f4e105_1280x974.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!I34K!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8e90f393-01d3-418a-b297-c5ff95f4e105_1280x974.png 424w, https://substackcdn.com/image/fetch/$s_!I34K!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8e90f393-01d3-418a-b297-c5ff95f4e105_1280x974.png 848w, https://substackcdn.com/image/fetch/$s_!I34K!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8e90f393-01d3-418a-b297-c5ff95f4e105_1280x974.png 1272w, https://substackcdn.com/image/fetch/$s_!I34K!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8e90f393-01d3-418a-b297-c5ff95f4e105_1280x974.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!I34K!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8e90f393-01d3-418a-b297-c5ff95f4e105_1280x974.png" width="1280" height="974" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/8e90f393-01d3-418a-b297-c5ff95f4e105_1280x974.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:974,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:33424,&quot;alt&quot;:&quot;Table: $10,000 from 2 Jan 2013 to 28 Aug 2026. The best ATR coil version became $15,873 (3.44% a year), the same breakout without the coil $15,662 (3.34%), T-bills $12,591 (1.70%), SPY $68,027 (15.08%) and QQQ $123,005 (20.18%).&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: $10,000 from 2 Jan 2013 to 28 Aug 2026. The best ATR coil version became $15,873 (3.44% a year), the same breakout without the coil $15,662 (3.34%), T-bills $12,591 (1.70%), SPY $68,027 (15.08%) and QQQ $123,005 (20.18%)." title="Table: $10,000 from 2 Jan 2013 to 28 Aug 2026. The best ATR coil version became $15,873 (3.44% a year), the same breakout without the coil $15,662 (3.34%), T-bills $12,591 (1.70%), SPY $68,027 (15.08%) and QQQ $123,005 (20.18%)." srcset="https://substackcdn.com/image/fetch/$s_!I34K!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8e90f393-01d3-418a-b297-c5ff95f4e105_1280x974.png 424w, https://substackcdn.com/image/fetch/$s_!I34K!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8e90f393-01d3-418a-b297-c5ff95f4e105_1280x974.png 848w, https://substackcdn.com/image/fetch/$s_!I34K!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8e90f393-01d3-418a-b297-c5ff95f4e105_1280x974.png 1272w, https://substackcdn.com/image/fetch/$s_!I34K!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8e90f393-01d3-418a-b297-c5ff95f4e105_1280x974.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p><strong>Verdict: doesn't beat the bar.</strong></p><p><code>THE TRANSFERABLE PART</code></p><h2>Three checks for any win-rate claim</h2><ol><li><p><strong>Ask for the days in the market.</strong> A 90% win rate on one day in twenty leaves nineteen days earning cash. You need both numbers.</p></li><li><p><strong>Ask what $10,000 became.</strong> Put it next to the index over the same dates. A screenshot of winning trades cannot answer that.</p></li><li><p><strong>Delete the clever part.</strong> Rerun the rule without its special filter. If the result stays, the filter was decoration.</p></li></ol><div class="subscription-widget-wrap-editor" data-attrs="{&quot;url&quot;:&quot;https://www.pastperformancelab.com/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe&quot;,&quot;language&quot;:&quot;en&quot;}" data-component-name="SubscribeWidgetToDOM"><div class="subscription-widget show-subscribe"><div class="preamble"><p class="cta-caption">One strategy tested every Tuesday. Free.</p></div><form class="subscription-widget-subscribe"><input type="email" class="email-input" name="email" placeholder="Type your email&#8230;" tabindex="-1"><input type="submit" class="button primary" value="Subscribe"><div class="fake-input-wrapper"><div class="fake-input"></div><div class="fake-button"></div></div></form></div></div><h3>Your turn</h3><p>Send us the strategy you are about to risk money on. Reply to this email or leave a comment with a link and the rules as you understand them. We test the ones readers ask for most.</p><div><hr></div><h2>For the quants</h2><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!9z-j!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F633ae836-1fe8-432a-ae37-ced24e3274e5_1280x1050.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!9z-j!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F633ae836-1fe8-432a-ae37-ced24e3274e5_1280x1050.png 424w, https://substackcdn.com/image/fetch/$s_!9z-j!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F633ae836-1fe8-432a-ae37-ced24e3274e5_1280x1050.png 848w, https://substackcdn.com/image/fetch/$s_!9z-j!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F633ae836-1fe8-432a-ae37-ced24e3274e5_1280x1050.png 1272w, https://substackcdn.com/image/fetch/$s_!9z-j!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F633ae836-1fe8-432a-ae37-ced24e3274e5_1280x1050.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!9z-j!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F633ae836-1fe8-432a-ae37-ced24e3274e5_1280x1050.png" width="1280" height="1050" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/633ae836-1fe8-432a-ae37-ced24e3274e5_1280x1050.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1050,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:47162,&quot;alt&quot;:&quot;Table: Triple RSI with cash when out: CAGR 6.13%, Sharpe 0.72, maximum drawdown &#8722;13.8%, volatility 5.1%, $1 becomes 7.05; SPY buy and hold: CAGR 10.89%, Sharpe 0.52, maximum drawdown &#8722;55.2%, volatility 18.7%, $1 becomes 29.84; SPY plus 1&#215; on signal days: CAGR 14.56%, Sharpe 0.64, maximum drawdown &#8722;55.2%, volatility 20.7%, $1 becomes 87.04; Triple RSI levered 3.66&#215; to SPY volatility (hindsight): CAGR 15.06%, Sharpe 0.72, maximum drawdown &#8722;45.4%, volatility 18.7%, $1 becomes 100.38; SPY scaled to 0.273&#215; to match Triple RSI volatility: CAGR 5.06%, Sharpe 0.52, maximum drawdown &#8722;16.8%, volatility 5.1%, $1 becomes 5.06.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: Triple RSI with cash when out: CAGR 6.13%, Sharpe 0.72, maximum drawdown &#8722;13.8%, volatility 5.1%, $1 becomes 7.05; SPY buy and hold: CAGR 10.89%, Sharpe 0.52, maximum drawdown &#8722;55.2%, volatility 18.7%, $1 becomes 29.84; SPY plus 1&#215; on signal days: CAGR 14.56%, Sharpe 0.64, maximum drawdown &#8722;55.2%, volatility 20.7%, $1 becomes 87.04; Triple RSI levered 3.66&#215; to SPY volatility (hindsight): CAGR 15.06%, Sharpe 0.72, maximum drawdown &#8722;45.4%, volatility 18.7%, $1 becomes 100.38; SPY scaled to 0.273&#215; to match Triple RSI volatility: CAGR 5.06%, Sharpe 0.52, maximum drawdown &#8722;16.8%, volatility 5.1%, $1 becomes 5.06." title="Table: Triple RSI with cash when out: CAGR 6.13%, Sharpe 0.72, maximum drawdown &#8722;13.8%, volatility 5.1%, $1 becomes 7.05; SPY buy and hold: CAGR 10.89%, Sharpe 0.52, maximum drawdown &#8722;55.2%, volatility 18.7%, $1 becomes 29.84; SPY plus 1&#215; on signal days: CAGR 14.56%, Sharpe 0.64, maximum drawdown &#8722;55.2%, volatility 20.7%, $1 becomes 87.04; Triple RSI levered 3.66&#215; to SPY volatility (hindsight): CAGR 15.06%, Sharpe 0.72, maximum drawdown &#8722;45.4%, volatility 18.7%, $1 becomes 100.38; SPY scaled to 0.273&#215; to match Triple RSI volatility: CAGR 5.06%, Sharpe 0.52, maximum drawdown &#8722;16.8%, volatility 5.1%, $1 becomes 5.06." srcset="https://substackcdn.com/image/fetch/$s_!9z-j!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F633ae836-1fe8-432a-ae37-ced24e3274e5_1280x1050.png 424w, https://substackcdn.com/image/fetch/$s_!9z-j!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F633ae836-1fe8-432a-ae37-ced24e3274e5_1280x1050.png 848w, https://substackcdn.com/image/fetch/$s_!9z-j!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F633ae836-1fe8-432a-ae37-ced24e3274e5_1280x1050.png 1272w, https://substackcdn.com/image/fetch/$s_!9z-j!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F633ae836-1fe8-432a-ae37-ced24e3274e5_1280x1050.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><ul><li><p>Trades (to 21 Sep 2026): 91; 90.1% wins; +134.5 bp average; profit factor 7.09; t 7.14; average hold 4.7 trading days; worst &#8722;7.4%, best +7.8%. Exposure 5.15%. Cash alone: 2.45% a year.</p></li><li><p>Overlay (the +1&#215; stream, excess over cash): +366 bp a year, t 4.09. By calendar year (1993 and 2026 partial): ahead of SPY in 27 of 34, behind in 4 (1994, 2011, 2025, 2026 to date), level in 3 (2001, 2002, 2008: no signals).</p></li><li><p>Halves: 11 Nov 1993 &#8211; 13 Apr 2010: 7.44% vs SPY 7.85% (38 trades, 92.1% wins, t 6.47). 14 Apr 2010 &#8211; 21 Sep 2026: 4.83% vs 14.01% (53 trades, 88.7% wins, t 4.16). Since 2020: 5.37% vs 15.56% (21 trades, 81.0% wins, t 2.26); SPY + 1&#215; 18.06%.</p></li><li><p>Costs: 6.24% at 0 bp, 6.13% at 2 bp, 6.01% at 4 bp per side. Signals on the unadjusted close: 90 trades, 90.0% wins, 5.96%.</p></li><li><p>Neighbourhood, 18 cells including the published one (entry 25/30/35 &#215; exit 40/50/60 &#215; prior 50/60): wins 82&#8211;92%, t &#8805; 3.08, CAGR 4.10&#8211;6.41%. No cell is near SPY's 10.89%.</p></li><li><p>QQQ, 21 Dec 1999 &#8211; 22 Sep 2026: 76 trades, 81.6% wins, t 4.18. Alone 5.01% vs QQQ 9.17%; QQQ + 1&#215; 11.96% (max DD &#8722;82.8% vs &#8722;83.0%); overlay +322 bp a year, t 2.43; ahead in 21 of 28 years.</p></li><li><p>SPY rules against the QQQ bar, 22 Dec 1999 &#8211; 22 Sep 2026: SPY 8.38%, SPY + 1&#215; 11.43%, QQQ 8.96%.</p></li></ul><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!9IeW!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1778864a-9caa-4517-a5f8-e56c590b0bf2_1280x1422.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!9IeW!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1778864a-9caa-4517-a5f8-e56c590b0bf2_1280x1422.png 424w, https://substackcdn.com/image/fetch/$s_!9IeW!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1778864a-9caa-4517-a5f8-e56c590b0bf2_1280x1422.png 848w, https://substackcdn.com/image/fetch/$s_!9IeW!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1778864a-9caa-4517-a5f8-e56c590b0bf2_1280x1422.png 1272w, https://substackcdn.com/image/fetch/$s_!9IeW!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1778864a-9caa-4517-a5f8-e56c590b0bf2_1280x1422.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!9IeW!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1778864a-9caa-4517-a5f8-e56c590b0bf2_1280x1422.png" width="1280" height="1422" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/1778864a-9caa-4517-a5f8-e56c590b0bf2_1280x1422.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1422,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:58577,&quot;alt&quot;:&quot;Table, 2 Jan 2013 to 28 Aug 2026: QQQ buy and hold: CAGR 20.18%, maximum drawdown &#8722;35.1%, $10,000 becomes $123,005; SPY buy and hold: CAGR 15.08%, maximum drawdown &#8722;33.7%, $10,000 becomes $68,027; QQQ plus 1&#215; on signal days: CAGR 23.40%, maximum drawdown &#8722;38.3%, $10,000 becomes $176,425; SPY plus 1&#215; on signal days: CAGR 18.53%, maximum drawdown &#8722;34.1%, $10,000 becomes $101,789; Triple RSI on SPY alone (41 trades, 87.8% winners): CAGR 5.06%, maximum drawdown &#8722;7.3%, $10,000 becomes $19,624; Triple RSI on QQQ alone: CAGR 4.85%, maximum drawdown &#8722;11.9%, $10,000 becomes $19,084; ATR coil long 5/20: CAGR 3.44%, maximum drawdown &#8722;4.0%, $10,000 becomes $15,873; ATR breakout long without the coil: CAGR 3.34%, maximum drawdown &#8722;4.6%, $10,000 becomes $15,662; T-bills: CAGR 1.70%, maximum drawdown 0.0%, $10,000 becomes $12,591.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table, 2 Jan 2013 to 28 Aug 2026: QQQ buy and hold: CAGR 20.18%, maximum drawdown &#8722;35.1%, $10,000 becomes $123,005; SPY buy and hold: CAGR 15.08%, maximum drawdown &#8722;33.7%, $10,000 becomes $68,027; QQQ plus 1&#215; on signal days: CAGR 23.40%, maximum drawdown &#8722;38.3%, $10,000 becomes $176,425; SPY plus 1&#215; on signal days: CAGR 18.53%, maximum drawdown &#8722;34.1%, $10,000 becomes $101,789; Triple RSI on SPY alone (41 trades, 87.8% winners): CAGR 5.06%, maximum drawdown &#8722;7.3%, $10,000 becomes $19,624; Triple RSI on QQQ alone: CAGR 4.85%, maximum drawdown &#8722;11.9%, $10,000 becomes $19,084; ATR coil long 5/20: CAGR 3.44%, maximum drawdown &#8722;4.0%, $10,000 becomes $15,873; ATR breakout long without the coil: CAGR 3.34%, maximum drawdown &#8722;4.6%, $10,000 becomes $15,662; T-bills: CAGR 1.70%, maximum drawdown 0.0%, $10,000 becomes $12,591." title="Table, 2 Jan 2013 to 28 Aug 2026: QQQ buy and hold: CAGR 20.18%, maximum drawdown &#8722;35.1%, $10,000 becomes $123,005; SPY buy and hold: CAGR 15.08%, maximum drawdown &#8722;33.7%, $10,000 becomes $68,027; QQQ plus 1&#215; on signal days: CAGR 23.40%, maximum drawdown &#8722;38.3%, $10,000 becomes $176,425; SPY plus 1&#215; on signal days: CAGR 18.53%, maximum drawdown &#8722;34.1%, $10,000 becomes $101,789; Triple RSI on SPY alone (41 trades, 87.8% winners): CAGR 5.06%, maximum drawdown &#8722;7.3%, $10,000 becomes $19,624; Triple RSI on QQQ alone: CAGR 4.85%, maximum drawdown &#8722;11.9%, $10,000 becomes $19,084; ATR coil long 5/20: CAGR 3.44%, maximum drawdown &#8722;4.0%, $10,000 becomes $15,873; ATR breakout long without the coil: CAGR 3.34%, maximum drawdown &#8722;4.6%, $10,000 becomes $15,662; T-bills: CAGR 1.70%, maximum drawdown 0.0%, $10,000 becomes $12,591." srcset="https://substackcdn.com/image/fetch/$s_!9IeW!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1778864a-9caa-4517-a5f8-e56c590b0bf2_1280x1422.png 424w, https://substackcdn.com/image/fetch/$s_!9IeW!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1778864a-9caa-4517-a5f8-e56c590b0bf2_1280x1422.png 848w, https://substackcdn.com/image/fetch/$s_!9IeW!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1778864a-9caa-4517-a5f8-e56c590b0bf2_1280x1422.png 1272w, https://substackcdn.com/image/fetch/$s_!9IeW!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1778864a-9caa-4517-a5f8-e56c590b0bf2_1280x1422.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!PI3g!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F559bac0c-4815-4543-9e77-9326f7340ade_1280x960.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!PI3g!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F559bac0c-4815-4543-9e77-9326f7340ade_1280x960.png 424w, https://substackcdn.com/image/fetch/$s_!PI3g!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F559bac0c-4815-4543-9e77-9326f7340ade_1280x960.png 848w, https://substackcdn.com/image/fetch/$s_!PI3g!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F559bac0c-4815-4543-9e77-9326f7340ade_1280x960.png 1272w, https://substackcdn.com/image/fetch/$s_!PI3g!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F559bac0c-4815-4543-9e77-9326f7340ade_1280x960.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!PI3g!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F559bac0c-4815-4543-9e77-9326f7340ade_1280x960.png" width="1280" height="960" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/559bac0c-4815-4543-9e77-9326f7340ade_1280x960.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:960,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:47566,&quot;alt&quot;:&quot;Table: ATR coil breakout, all cells, net of costs. Long 5/20: 93 trades, 64.5% winners, 29.6 points a trade, profit factor 2.39, t 2.27, account 3.44% a year, maximum drawdown &#8722;3.96%, in the market 2.7% of days; Long 10/40: 92 trades, 63.0% winners, 7.4 points a trade, profit factor 1.29, t 1.43, account 2.50% a year, maximum drawdown &#8722;4.28%, in the market 2.7% of days; Long 14/50: 99 trades, 60.6% winners, 0.2 points a trade, profit factor 1.01, t 0.75, account 2.16% a year, maximum drawdown &#8722;8.27%, in the market 2.9% of days; Short 5/20: 166 trades, 48.2% winners, 16.7 points a trade, profit factor 1.72, t 1.31, account 2.69% a year, maximum drawdown &#8722;4.80%, in the market 4.9% of days; Short 10/40: 206 trades, 45.6% winners, 11.5 points a trade, profit factor 1.46, t 1.20, account 2.65% a year, maximum drawdown &#8722;6.64%, in the market 6.0% of days; Short 14/50: 222 trades, 46.8% winners, 15.8 points a trade, profit factor 1.62, t 1.72, account 3.20% a year, maximum drawdown &#8722;5.52%, in the market 6.5% of days; Long, no coil: 140 trades, 60.0% winners, 16.2 points a trade, profit factor 1.54, t 1.77, account 3.34% a year, maximum drawdown &#8722;4.57%, in the market 4.1% of days.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: ATR coil breakout, all cells, net of costs. Long 5/20: 93 trades, 64.5% winners, 29.6 points a trade, profit factor 2.39, t 2.27, account 3.44% a year, maximum drawdown &#8722;3.96%, in the market 2.7% of days; Long 10/40: 92 trades, 63.0% winners, 7.4 points a trade, profit factor 1.29, t 1.43, account 2.50% a year, maximum drawdown &#8722;4.28%, in the market 2.7% of days; Long 14/50: 99 trades, 60.6% winners, 0.2 points a trade, profit factor 1.01, t 0.75, account 2.16% a year, maximum drawdown &#8722;8.27%, in the market 2.9% of days; Short 5/20: 166 trades, 48.2% winners, 16.7 points a trade, profit factor 1.72, t 1.31, account 2.69% a year, maximum drawdown &#8722;4.80%, in the market 4.9% of days; Short 10/40: 206 trades, 45.6% winners, 11.5 points a trade, profit factor 1.46, t 1.20, account 2.65% a year, maximum drawdown &#8722;6.64%, in the market 6.0% of days; Short 14/50: 222 trades, 46.8% winners, 15.8 points a trade, profit factor 1.62, t 1.72, account 3.20% a year, maximum drawdown &#8722;5.52%, in the market 6.5% of days; Long, no coil: 140 trades, 60.0% winners, 16.2 points a trade, profit factor 1.54, t 1.77, account 3.34% a year, maximum drawdown &#8722;4.57%, in the market 4.1% of days." title="Table: ATR coil breakout, all cells, net of costs. Long 5/20: 93 trades, 64.5% winners, 29.6 points a trade, profit factor 2.39, t 2.27, account 3.44% a year, maximum drawdown &#8722;3.96%, in the market 2.7% of days; Long 10/40: 92 trades, 63.0% winners, 7.4 points a trade, profit factor 1.29, t 1.43, account 2.50% a year, maximum drawdown &#8722;4.28%, in the market 2.7% of days; Long 14/50: 99 trades, 60.6% winners, 0.2 points a trade, profit factor 1.01, t 0.75, account 2.16% a year, maximum drawdown &#8722;8.27%, in the market 2.9% of days; Short 5/20: 166 trades, 48.2% winners, 16.7 points a trade, profit factor 1.72, t 1.31, account 2.69% a year, maximum drawdown &#8722;4.80%, in the market 4.9% of days; Short 10/40: 206 trades, 45.6% winners, 11.5 points a trade, profit factor 1.46, t 1.20, account 2.65% a year, maximum drawdown &#8722;6.64%, in the market 6.0% of days; Short 14/50: 222 trades, 46.8% winners, 15.8 points a trade, profit factor 1.62, t 1.72, account 3.20% a year, maximum drawdown &#8722;5.52%, in the market 6.5% of days; Long, no coil: 140 trades, 60.0% winners, 16.2 points a trade, profit factor 1.54, t 1.77, account 3.34% a year, maximum drawdown &#8722;4.57%, in the market 4.1% of days." srcset="https://substackcdn.com/image/fetch/$s_!PI3g!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F559bac0c-4815-4543-9e77-9326f7340ade_1280x960.png 424w, https://substackcdn.com/image/fetch/$s_!PI3g!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F559bac0c-4815-4543-9e77-9326f7340ade_1280x960.png 848w, https://substackcdn.com/image/fetch/$s_!PI3g!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F559bac0c-4815-4543-9e77-9326f7340ade_1280x960.png 1272w, https://substackcdn.com/image/fetch/$s_!PI3g!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F559bac0c-4815-4543-9e77-9326f7340ade_1280x960.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><ul><li><p>Six cells were tried; the best t is 2.27. With six tries that is not evidence (a later issue on multiple testing covers why).</p></li><li><p>On the long side the result falls as the ATR periods lengthen (29.6 &#8594; 7.4 &#8594; 0.2 points a trade). The source did not publish the periods.</p></li><li><p>Per trade the coil filter nearly doubles the long average (29.6 against 16.2 points, on 93 trades against 140). In the account it adds about 0.1 point a year (3.44% against 3.34%).</p></li></ul><h3>Method</h3><p><strong>Triple RSI.</strong> Rules from the <a href="https://quantifiedstrategies.substack.com/p/triple-rsi-trading-strategy-enhance">Quantified Strategies page</a>, matched condition by condition on 17 Oct 2026. Buy at the close when RSI(5) &lt; 30, RSI(5) has fallen three days in a row, RSI(5) three days ago was &lt; 60 and the close is above the 200-day average. Sell at the close when RSI(5) crosses above 50. Wilder RSI. SPY and QQQ total return (Yahoo Finance), NYSE sessions. Cash and financing at the 3-month T-bill rate (FRED DTB3). 0.02% (2 bp) per side. CAGR over elapsed years; Sharpe on daily excess returns &#215; &#8730;252.</p><p><strong>Ties and price series.</strong> "Fallen" means strictly lower. When SPY closes unchanged, its RSI(5) does not move, and we never count that as a fall. Example: SPY closed flat on 22 Jul 1998, so 24 Jul 1998 was not a third straight fall, and the next entry came on 4 Aug. Reading unchanged days as falls instead gives 95 trades, 88.4% winners and 5.80% a year. Signals on unadjusted closes, as a price chart shows them, give 90 trades, 90.0% winners and 5.96% a year. The prices behind every number here are frozen in one file, downloaded on 18 Oct 2026.</p><p><strong>Add-on.</strong> Hold the index 100% always; on signal days add +1&#215; of the same fund, financed at the T-bill rate. A broker charges more: about 0.5&#8211;1.5 points on the borrowed slice, which at 5% exposure costs at most about 8 bp a year. The vol-matched leverage uses the full-sample volatility, so it is an illustration, not a tradeable rule.</p><p><strong>ATR coil.</strong> Dukascopy US Tech 100 index (a CFD on the index, bid prices), 1-minute, NYSE sessions only, placeholder minutes removed (<a href="https://www.pastperformancelab.com/p/dukascopy-data-placeholder-minutes-backtest">Issue 09</a> explains them). 14 NYSE sessions (12 in 2013, 2 in 2014) hold only placeholder minutes in the tape and are skipped; 20 more end early, which touches no trade of the best version. 30-minute bars from the open. Entry: a stop 2.5 &#215; ATR(20) above the bar's open (below, for shorts), filled at the first minute that trades through. Filter: short ATR below long ATR at the prior bar. Exit at the session's last minute. One trade a day. Cost: 1.0 index point per round trip. Account at 1&#215; notional; cash earns the daily T-bill series on every session in the run. Rules as we read them from partial captures.</p><p><strong>Cash series.</strong> Triple RSI uses FRED DTB3; the ATR rows and Table 4's T-bill row use our daily T-bill series. Over 2013&#8211;2026 they earn 1.76% and 1.70% a year; no verdict moves.</p><p>Full method: <a href="https://www.pastperformancelab.com/p/how-we-backtest-trading-strategies">How We Test a Trading Strategy</a>.</p><p><em>Past performance is no guarantee of future results. We check anyway.</em></p><p><em>This is research on historical data, not investment advice. <a href="https://www.pastperformancelab.com/about">Full disclaimer</a>.</em></p>]]></content:encoded></item><item><title><![CDATA[One in Ten Minutes of Free 2013 Nasdaq-100 CFD Data Is a Placeholder]]></title><description><![CDATA[Dukascopy's free minute files fill quiet minutes with flat, zero-volume candles and show quotes on US holidays. A 37-line check finds both.]]></description><link>https://www.pastperformancelab.com/p/dukascopy-data-placeholder-minutes-backtest</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/dukascopy-data-placeholder-minutes-backtest</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Tue, 29 Sep 2026 11:01:43 GMT</pubDate><enclosure url="https://substackcdn.com/image/fetch/$s_!YTDL!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F23c05511-b302-42cd-b9a0-cd7c803859da_1280x1132.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Issue 09 &#183; September 2026 &#183; 2 free tapes &#183; every cash minute since 2013</em></p><p><em>Updated 24 Oct 2026: reader tests now start with the first reader submission. The findings are unchanged.</em></p><p>Dukascopy, a Swiss bank, gives away one-minute candles for its index CFDs, and open-source tools download years of them with one command. We built our first intraday backtests on these files.</p><p>Then we checked every cash-session minute against the NYSE calendar. In 2013, about one cash minute in ten is a placeholder: a flat candle with zero volume, written because no quote arrived. And the files show quotes on 84 days when the NYSE was closed.</p><p><strong>As downloaded, free Dukascopy minute data is not ready for a backtest: drop the placeholder minutes and the non-NYSE days first.</strong><br><em>Checked: every one-minute candle in two tapes, the US Tech 100 and US 500 index CFDs (bid side), on NYSE sessions from January 2013 to August 2026.</em></p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!YTDL!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F23c05511-b302-42cd-b9a0-cd7c803859da_1280x1132.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!YTDL!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F23c05511-b302-42cd-b9a0-cd7c803859da_1280x1132.png 424w, https://substackcdn.com/image/fetch/$s_!YTDL!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F23c05511-b302-42cd-b9a0-cd7c803859da_1280x1132.png 848w, https://substackcdn.com/image/fetch/$s_!YTDL!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F23c05511-b302-42cd-b9a0-cd7c803859da_1280x1132.png 1272w, https://substackcdn.com/image/fetch/$s_!YTDL!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F23c05511-b302-42cd-b9a0-cd7c803859da_1280x1132.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!YTDL!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F23c05511-b302-42cd-b9a0-cd7c803859da_1280x1132.png" width="1280" height="1132" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/23c05511-b302-42cd-b9a0-cd7c803859da_1280x1132.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1132,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:40612,&quot;alt&quot;:&quot;Table: placeholder share of NYSE cash-session minutes, US Tech 100 versus US 500. 2013: 10.6% and 11.2% (US 500 from April). 2014: 3.1% and 7.2%. Worst year from 2015: 0.5% (2015) and 4.3% (2017). Highest year 2020&#8211;2026: 0.1% (2026) and 0.2% (2020). Missing minutes: 0 and 0. Non-NYSE days with cash-hour quotes: 84 and 84.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: placeholder share of NYSE cash-session minutes, US Tech 100 versus US 500. 2013: 10.6% and 11.2% (US 500 from April). 2014: 3.1% and 7.2%. Worst year from 2015: 0.5% (2015) and 4.3% (2017). Highest year 2020&#8211;2026: 0.1% (2026) and 0.2% (2020). Missing minutes: 0 and 0. Non-NYSE days with cash-hour quotes: 84 and 84." title="Table: placeholder share of NYSE cash-session minutes, US Tech 100 versus US 500. 2013: 10.6% and 11.2% (US 500 from April). 2014: 3.1% and 7.2%. Worst year from 2015: 0.5% (2015) and 4.3% (2017). Highest year 2020&#8211;2026: 0.1% (2026) and 0.2% (2020). Missing minutes: 0 and 0. Non-NYSE days with cash-hour quotes: 84 and 84." srcset="https://substackcdn.com/image/fetch/$s_!YTDL!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F23c05511-b302-42cd-b9a0-cd7c803859da_1280x1132.png 424w, https://substackcdn.com/image/fetch/$s_!YTDL!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F23c05511-b302-42cd-b9a0-cd7c803859da_1280x1132.png 848w, https://substackcdn.com/image/fetch/$s_!YTDL!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F23c05511-b302-42cd-b9a0-cd7c803859da_1280x1132.png 1272w, https://substackcdn.com/image/fetch/$s_!YTDL!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F23c05511-b302-42cd-b9a0-cd7c803859da_1280x1132.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p><code>01 / WHAT A PLACEHOLDER IS</code></p><h2>A placeholder is a minute in which nothing was quoted</h2><p>Each Dukascopy day file holds 1,440 one-minute candles, one per minute. When no quote arrives in a minute, the file still gets a candle. Its open, high, low and close all equal the last price, and its volume is zero.</p><p>Take Tuesday 5 November 2013. Inside the cash session, 20 minutes of the US Tech 100 file are placeholders (Figure 1).</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!rWM5!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F810d15cd-aa12-44d6-8292-2dac5e7eccae_1280x998.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!rWM5!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F810d15cd-aa12-44d6-8292-2dac5e7eccae_1280x998.png 424w, https://substackcdn.com/image/fetch/$s_!rWM5!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F810d15cd-aa12-44d6-8292-2dac5e7eccae_1280x998.png 848w, https://substackcdn.com/image/fetch/$s_!rWM5!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F810d15cd-aa12-44d6-8292-2dac5e7eccae_1280x998.png 1272w, https://substackcdn.com/image/fetch/$s_!rWM5!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F810d15cd-aa12-44d6-8292-2dac5e7eccae_1280x998.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!rWM5!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F810d15cd-aa12-44d6-8292-2dac5e7eccae_1280x998.png" width="1280" height="998" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/810d15cd-aa12-44d6-8292-2dac5e7eccae_1280x998.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:998,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:38661,&quot;alt&quot;:&quot;Line chart of US Tech 100 index CFD one-minute closes on Tuesday 5 November 2013, 09:30 to 16:00 ET: 390 cash minutes, closes between 3,360.77 and 3,394.92. 20 of the minutes are placeholders, marked in red, in 2 runs between 14:15 and 15:04 ET; the first run starts at 14:15 ET and lasts 15 minutes, and the price line is flat through every placeholder.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Line chart of US Tech 100 index CFD one-minute closes on Tuesday 5 November 2013, 09:30 to 16:00 ET: 390 cash minutes, closes between 3,360.77 and 3,394.92. 20 of the minutes are placeholders, marked in red, in 2 runs between 14:15 and 15:04 ET; the first run starts at 14:15 ET and lasts 15 minutes, and the price line is flat through every placeholder." title="Line chart of US Tech 100 index CFD one-minute closes on Tuesday 5 November 2013, 09:30 to 16:00 ET: 390 cash minutes, closes between 3,360.77 and 3,394.92. 20 of the minutes are placeholders, marked in red, in 2 runs between 14:15 and 15:04 ET; the first run starts at 14:15 ET and lasts 15 minutes, and the price line is flat through every placeholder." srcset="https://substackcdn.com/image/fetch/$s_!rWM5!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F810d15cd-aa12-44d6-8292-2dac5e7eccae_1280x998.png 424w, https://substackcdn.com/image/fetch/$s_!rWM5!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F810d15cd-aa12-44d6-8292-2dac5e7eccae_1280x998.png 848w, https://substackcdn.com/image/fetch/$s_!rWM5!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F810d15cd-aa12-44d6-8292-2dac5e7eccae_1280x998.png 1272w, https://substackcdn.com/image/fetch/$s_!rWM5!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F810d15cd-aa12-44d6-8292-2dac5e7eccae_1280x998.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p>We did not make these candles. We downloaded that day again, straight from Dukascopy, on 21 September 2026. The same 20 minutes are there.</p><p><code>02 / WHEN THEY HAPPEN</code></p><h2>Placeholders crowd the early years</h2><p>In the US Tech 100 file, placeholders fall from a tenth of cash minutes in 2013 to under 1% two years later. The US 500 cleans up later and relapses once (Figure 2). Both are nearly clean in recent years.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!VBbM!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd6797b04-0451-4d85-a847-3304613085ee_1280x1030.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!VBbM!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd6797b04-0451-4d85-a847-3304613085ee_1280x1030.png 424w, https://substackcdn.com/image/fetch/$s_!VBbM!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd6797b04-0451-4d85-a847-3304613085ee_1280x1030.png 848w, https://substackcdn.com/image/fetch/$s_!VBbM!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd6797b04-0451-4d85-a847-3304613085ee_1280x1030.png 1272w, https://substackcdn.com/image/fetch/$s_!VBbM!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd6797b04-0451-4d85-a847-3304613085ee_1280x1030.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!VBbM!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd6797b04-0451-4d85-a847-3304613085ee_1280x1030.png" width="1280" height="1030" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/d6797b04-0451-4d85-a847-3304613085ee_1280x1030.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1030,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:37182,&quot;alt&quot;:&quot;Line chart, 2013 to 2026: share of NYSE cash-session minutes that are placeholders, by year. US Tech 100 falls from 10.6% in 2013 to 3.1% in 2014 and 0.5% in 2015, and is at or below 0.1% in every later year. US 500 (from April 2013) falls from 11.2% to 7.2% in 2014, relapses to 4.3% in 2017 after 0.4% in 2016, and is at or below 0.2% from 2020.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Line chart, 2013 to 2026: share of NYSE cash-session minutes that are placeholders, by year. US Tech 100 falls from 10.6% in 2013 to 3.1% in 2014 and 0.5% in 2015, and is at or below 0.1% in every later year. US 500 (from April 2013) falls from 11.2% to 7.2% in 2014, relapses to 4.3% in 2017 after 0.4% in 2016, and is at or below 0.2% from 2020." title="Line chart, 2013 to 2026: share of NYSE cash-session minutes that are placeholders, by year. US Tech 100 falls from 10.6% in 2013 to 3.1% in 2014 and 0.5% in 2015, and is at or below 0.1% in every later year. US 500 (from April 2013) falls from 11.2% to 7.2% in 2014, relapses to 4.3% in 2017 after 0.4% in 2016, and is at or below 0.2% from 2020." srcset="https://substackcdn.com/image/fetch/$s_!VBbM!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd6797b04-0451-4d85-a847-3304613085ee_1280x1030.png 424w, https://substackcdn.com/image/fetch/$s_!VBbM!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd6797b04-0451-4d85-a847-3304613085ee_1280x1030.png 848w, https://substackcdn.com/image/fetch/$s_!VBbM!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd6797b04-0451-4d85-a847-3304613085ee_1280x1030.png 1272w, https://substackcdn.com/image/fetch/$s_!VBbM!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd6797b04-0451-4d85-a847-3304613085ee_1280x1030.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p>How you download matters too. <a href="https://www.dukascopy-node.app/config/node">dukascopy-node</a>, an open-source downloader, drops zero-volume candles by default; its docs say they come mainly from weekends and bank holidays. The same minutes then show up as gaps, and a forward-fill in your code quietly puts them back.</p><p><code>03 / WHAT THEY DO TO A BACKTEST</code></p><h2>A placeholder fills your order at a stale price</h2><p>Three things go wrong. An order that fills on a placeholder gets the last quote, which may be minutes old. An opening range built partly from placeholders looks calmer than the market was. And any rule that measures minute ranges sees smaller ones than the market had.</p><p>The risk is largest in the years with the most placeholders, 2013 and 2014. In <a href="https://www.pastperformancelab.com/p/saty-phase-oscillator-backtest-out-of-sample">Issue 06</a>, most of the out-of-sample shortfall against buy-and-hold comes from those two years. We cannot tell how much of it is the strategy and how much the data, which is one reason that verdict now reads unproven.</p><p><code>04 / THE HOLIDAY PROBLEM</code></p><h2>The files trade on days the NYSE never opened</h2><p>Count the US Tech 100 day files as sessions and you get more than 4,200 "days" since 2013, one in six of them a Sunday.</p><p>The NYSE was open on about 3,400 of them. On 84 weekdays when it was closed, all of them holidays such as Thanksgiving and the Fourth of July, the file still shows quotes during cash hours.</p><p>A backtest on the tape's own calendar trades those days, and one that counts rows as trading days annualises its returns wrongly. Our back issues now use NYSE sessions (updated 27 September).</p><h3>The transferable part</h3><ol><li><p><strong>Count placeholders inside the session.</strong> A placeholder has open = high = low = close and zero volume. Drop them before you build 5- or 10-minute bars, and never fill an order on one.</p></li><li><p><strong>Put every frame on the exchange calendar.</strong> pandas_market_calendars gives NYSE sessions, holidays and early closes. Take no entries on days the exchange was closed.</p></li><li><p><strong>Count missing minutes too.</strong> If your downloader drops zero-volume candles, placeholders turn into gaps. Check what your code does with a gap before it fills one.</p></li></ol><p>Here is the checker we ran. It is 37 lines of Python and needs pandas and pandas_market_calendars. It reports each check by year.</p><pre><code>#!/usr/bin/env python3
"""tape_check.py - does your 1-minute data hold every minute the NYSE was open?
Usage:  python tape_check.py your_data.csv [--tz UTC]      (--tz = timezone of your timestamps)
Needs:  pip install pandas pandas_market_calendars
Input:  a timestamp column plus open, high, low, close, volume (any capitalisation; o/h/l/c/v also work)."""
import sys
import pandas as pd, pandas_market_calendars as mcal

path = sys.argv[1]
tz = sys.argv[sys.argv.index('--tz') + 1] if '--tz' in sys.argv else 'UTC'
df = pd.read_parquet(path) if path.endswith('.parquet') else pd.read_csv(path)
df.columns = [c.strip().lower() for c in df.columns]
df = df.rename(columns={'open': 'o', 'high': 'h', 'low': 'l', 'close': 'c', 'volume': 'v'})
t = df[next(c for c in df.columns if c not in ('o', 'h', 'l', 'c', 'v'))]
if pd.api.types.is_numeric_dtype(t):
    t = pd.to_datetime(t, unit='ms' if t.max() &gt; 1e12 else 's', utc=True)   # epoch timestamps
t = pd.to_datetime(t)
t = t.dt.tz_localize(tz) if t.dt.tz is None else t
df.index = pd.DatetimeIndex(t.dt.tz_convert('America/New_York'))
df = df[~df.index.duplicated()]
full = mcal.get_calendar('NYSE').schedule(df.index.min().date(), df.index.max().date())
sched = full[(full.market_open &gt;= df.index.min()) &amp; (full.market_close &lt;= df.index.max() + pd.Timedelta(minutes=1))]  # whole sessions only
want = mcal.date_range(sched, frequency='1min', closed='left', force_close=False).tz_convert('America/New_York')
flat = (df.o == df.h) &amp; (df.h == df.l) &amp; (df.l == df.c) &amp; (df.v == 0)   # a bar where nothing traded
got = df.index.intersection(want)
yr = pd.DataFrame({'open minutes': pd.Series(1, index=want).groupby(want.year).sum(),
                   'missing': pd.Series(~want.isin(df.index), index=want).groupby(want.year).sum(),
                   'flat, zero volume': flat[got].groupby(got.year).sum()}).fillna(0).astype(int)
yr['missing %'] = (100 * yr['missing'] / yr['open minutes']).round(1)
yr['flat %'] = (100 * yr['flat, zero volume'] / yr['open minutes']).round(1)
print(yr.to_string())
cash = df.between_time('09:30', '15:59')
traded = cash.index[~flat[cash.index].to_numpy()]
closed = sorted(set(traded.date) - set(full.index.date))
print('\nDays with trades at 09:30-16:00 ET while the NYSE was closed: %d  %s' % (len(closed), [str(d) for d in closed[:8]]))
print('Flat and missing minutes are prices your backtest never really had. If the numbers look odd, check --tz first:')
print('a wrong timezone shifts the session and shows up as extra flat or missing minutes and closed-day trades.')</code></pre><p><strong>Usage:</strong> <code>python tape_check.py your_data.csv [--tz UTC]</code> (a <code>.parquet</code> path works too; <code>--tz</code> names the timezone of your timestamps and defaults to UTC).</p><div class="subscription-widget-wrap-editor" data-attrs="{&quot;url&quot;:&quot;https://www.pastperformancelab.com/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe&quot;,&quot;language&quot;:&quot;en&quot;}" data-component-name="SubscribeWidgetToDOM"><div class="subscription-widget show-subscribe"><div class="preamble"><p class="cta-caption">One strategy tested every Tuesday. Free.</p></div><form class="subscription-widget-subscribe"><input type="email" class="email-input" name="email" placeholder="Type your email&#8230;" tabindex="-1"><input type="submit" class="button primary" value="Subscribe"><div class="fake-input-wrapper"><div class="fake-input"></div><div class="fake-button"></div></div></form></div></div><h3>Your turn</h3><p>Send us the strategy you are about to risk money on. The first reader submission becomes Reader Test #1. Reply to this email, or write to pastperformancelab@protonmail.com.</p><h3>Method</h3><p><strong>Data.</strong> Dukascopy one-minute bid candles for two index CFDs: US Tech 100 (USATECHIDXUSD) from January 2013 and US 500 (USA500IDXUSD) from April 2013, to 28 and 31 August 2026 respectively. We download Dukascopy's own per-day files and add nothing: no forward fill, no repair.</p><p><strong>Calendar.</strong> NYSE sessions from pandas_market_calendars, with holidays and early closes, whole sessions only. Cash minutes run from 09:30 ET to 16:00 ET, or to the early close.</p><p><strong>Definitions.</strong> A placeholder minute has open = high = low = close and volume 0. A missing minute is a cash minute with no candle. A non-NYSE day is a weekday on which the NYSE was closed and the file has quotes between 09:30 and 16:00 ET.</p><p><strong>Raw check.</strong> On 21 September 2026 we downloaded the 5 November 2013 file again from Dukascopy. All 390 cash-session closes match our tape exactly, and so do the 20 placeholder minutes.</p><p><strong>Checker tests.</strong> On a synthetic file with planted defects (15 missing minutes, 20 placeholders, quotes on Thanksgiving, the 29 November early close and a partial first day), the checker returns the exact counts.</p><p><strong>Right of reply.</strong> We sent these findings to Dukascopy on 23 September. Dukascopy acknowledged receipt but had not replied by 28 September.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!m2VF!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F26d666f1-3d42-4787-94d1-22528239ef15_1280x2446.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!m2VF!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F26d666f1-3d42-4787-94d1-22528239ef15_1280x2446.png 424w, https://substackcdn.com/image/fetch/$s_!m2VF!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F26d666f1-3d42-4787-94d1-22528239ef15_1280x2446.png 848w, https://substackcdn.com/image/fetch/$s_!m2VF!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F26d666f1-3d42-4787-94d1-22528239ef15_1280x2446.png 1272w, https://substackcdn.com/image/fetch/$s_!m2VF!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F26d666f1-3d42-4787-94d1-22528239ef15_1280x2446.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!m2VF!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F26d666f1-3d42-4787-94d1-22528239ef15_1280x2446.png" width="1280" height="2446" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/26d666f1-3d42-4787-94d1-22528239ef15_1280x2446.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:2446,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:93068,&quot;alt&quot;:&quot;Table: results by year, 2013 to 2026, for both tapes: NYSE sessions, cash minutes, placeholder minutes and share, missing minutes and non-NYSE days. Totals: US Tech 100 3,435 sessions, 1,334,430 cash minutes, 14,339 placeholder minutes (1.1%), 0 missing, 84 non-NYSE days; US 500 3,365 sessions, 1,307,130 cash minutes, 23,231 placeholder minutes (1.8%), 0 missing, 84 non-NYSE days.&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: results by year, 2013 to 2026, for both tapes: NYSE sessions, cash minutes, placeholder minutes and share, missing minutes and non-NYSE days. Totals: US Tech 100 3,435 sessions, 1,334,430 cash minutes, 14,339 placeholder minutes (1.1%), 0 missing, 84 non-NYSE days; US 500 3,365 sessions, 1,307,130 cash minutes, 23,231 placeholder minutes (1.8%), 0 missing, 84 non-NYSE days." title="Table: results by year, 2013 to 2026, for both tapes: NYSE sessions, cash minutes, placeholder minutes and share, missing minutes and non-NYSE days. Totals: US Tech 100 3,435 sessions, 1,334,430 cash minutes, 14,339 placeholder minutes (1.1%), 0 missing, 84 non-NYSE days; US 500 3,365 sessions, 1,307,130 cash minutes, 23,231 placeholder minutes (1.8%), 0 missing, 84 non-NYSE days." srcset="https://substackcdn.com/image/fetch/$s_!m2VF!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F26d666f1-3d42-4787-94d1-22528239ef15_1280x2446.png 424w, https://substackcdn.com/image/fetch/$s_!m2VF!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F26d666f1-3d42-4787-94d1-22528239ef15_1280x2446.png 848w, https://substackcdn.com/image/fetch/$s_!m2VF!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F26d666f1-3d42-4787-94d1-22528239ef15_1280x2446.png 1272w, https://substackcdn.com/image/fetch/$s_!m2VF!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F26d666f1-3d42-4787-94d1-22528239ef15_1280x2446.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p><em>Past performance is no guarantee of future results. We check anyway.</em></p><p><em>This is research on historical data, not investment advice. <a href="https://www.pastperformancelab.com/about">Full disclaimer</a>.</em></p>]]></content:encoded></item><item><title><![CDATA[Start Here: How to Check a Trading Strategy]]></title><description><![CDATA[What the Lab does, how to read a verdict, and the three issues to read first.]]></description><link>https://www.pastperformancelab.com/p/trading-strategy-backtest-verdicts</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/trading-strategy-backtest-verdicts</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Mon, 28 Sep 2026 08:46:59 GMT</pubDate><enclosure url="https://substackcdn.com/image/fetch/$s_!jDh6!,w_256,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0939f4d1-f253-496c-919e-84b675c82eed_512x512.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Start here &#183; updated 12 November 2026</em></p><p>Past Performance Lab checks trading strategies before you risk money on them. We rebuild each strategy from its author's own rules. Then we test it the way your account would live it.</p><p>That means three things. Every trade pays trading costs. Money waiting out of the market earns only Treasury bill interest. And the result is compared with simply holding the index, through one fund such as QQQ or SPY.</p><h3>What we keep finding</h3><p>Many strategies have a real strength, such as a high win rate or a smaller worst fall. Then we count what the account made. A strategy that waits in cash most days misses much of the market's growth. So far, none has cleanly beaten simply holding the index.</p><p>Every test is on the <a href="https://www.pastperformancelab.com/p/backtested-trading-strategies-vs-buy-and-hold">Scoreboard</a>, one block per strategy: the claim, our result, the index, the verdict.</p><h3>How to read a verdict</h3><ul><li><p><strong>Fails:</strong> no real profit after trading costs.</p></li><li><p><strong>Loses to the index:</strong> the edge is real, but the account ends behind simply holding the index.</p></li><li><p><strong>Unproven:</strong> the data cannot yet tell a real edge from luck or tuning.</p></li><li><p><strong>Replicates:</strong> the author's own claim checks out on our data. That alone says nothing about the index.</p></li><li><p><strong>Works as an add-on:</strong> weak alone, but it helped when kept on top of an index holding. We say how strong the evidence is.</p></li></ul><p>Each block also answers one question: should you use it? The answer is No, Only as an add-on, or Maybe. Issues that study data rather than a strategy say so.</p><h3>Three issues to read first</h3><ol><li><p><a href="https://www.pastperformancelab.com/p/triple-rsi-strategy-backtest">Nine Wins in Ten, a Quarter of the Money</a> (Issue 10). The plainest example of winning trades that still lose money. It opens with a 60-second verdict.</p></li><li><p><a href="https://www.pastperformancelab.com/p/spx-put-credit-spread-backtest-2020">The Missing Ten Weeks</a> (Issue 03). A 95% win rate that is real, and a start date that hides the risk. Read it before you trust a short backtest.</p></li><li><p><a href="https://www.pastperformancelab.com/p/backtest-vs-live-trading-47-second-delay">The 47-Second Tax</a> (Issue 07). Real orders fill later than a backtest assumes. This issue measures what the wait costs.</p></li></ol><h3>Where to go next</h3><ul><li><p><a href="https://www.pastperformancelab.com/p/backtested-trading-strategies-vs-buy-and-hold">The Scoreboard</a>: every verdict so far, newest first.</p></li><li><p><a href="https://www.pastperformancelab.com/p/how-we-backtest-trading-strategies">How We Test a Trading Strategy</a>: the checks every strategy goes through, and what each verdict means.</p></li><li><p><a href="https://www.pastperformancelab.com/about">About</a>: who we are, and the full disclaimer.</p></li></ul><div class="subscription-widget-wrap-editor" data-attrs="{&quot;url&quot;:&quot;https://www.pastperformancelab.com/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe&quot;,&quot;language&quot;:&quot;en&quot;}" data-component-name="SubscribeWidgetToDOM"><div class="subscription-widget show-subscribe"><div class="preamble"><p class="cta-caption">One strategy tested every Tuesday. Free.</p></div><form class="subscription-widget-subscribe"><input type="email" class="email-input" name="email" placeholder="Type your email&#8230;" tabindex="-1"><input type="submit" class="button primary" value="Subscribe"><div class="fake-input-wrapper"><div class="fake-input"></div><div class="fake-button"></div></div></form></div></div><h3>Your turn</h3><p>Send us the strategy you are about to risk money on. Write to pastperformancelab@protonmail.com.</p><div><hr></div><p>Full method: <a href="https://www.pastperformancelab.com/p/how-we-backtest-trading-strategies">How We Test a Trading Strategy</a>.</p><p><em>Past performance is no guarantee of future results. We check anyway.</em></p><p><em>This is research on historical data, not investment advice. <a href="https://www.pastperformancelab.com/about">Full disclaimer</a>.</em></p>]]></content:encoded></item><item><title><![CDATA[How We Test a Trading Strategy]]></title><description><![CDATA[The checks every strategy goes through before we publish a verdict, in plain words first.]]></description><link>https://www.pastperformancelab.com/p/how-we-backtest-trading-strategies</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/how-we-backtest-trading-strategies</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Mon, 28 Sep 2026 08:46:57 GMT</pubDate><enclosure url="https://substackcdn.com/image/fetch/$s_!jDh6!,w_256,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0939f4d1-f253-496c-919e-84b675c82eed_512x512.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>The method behind every verdict &#183; updated 12 November 2026</em></p><p>We test trading strategies the way your account would live them. Every issue follows the same steps, in this order. Each step says it plainly first, then precisely.</p><ol><li><p><strong>Rules first.</strong> We rebuild each strategy from its author's own rules and write down every assumption.</p><p>Then we reproduce the author's claim on the author's own window. If it does not reproduce, we say so and ask the author.</p></li><li><p><strong>Data frozen before the test.</strong> Before we run a test, we save its prices in one file. Every number in the issue comes from that file.</p><p><em>Precisely:</em> recent issues print the file's md5 fingerprint and its last session, so anyone can confirm the data did not change.</p></li><li><p><strong>Clean data, on the exchange's calendar.</strong> We use only days the New York Stock Exchange was open, and we remove fake minutes from free data.</p><p><em>Precisely:</em> daily tests use ETF prices with dividends reinvested. Intraday tests use Dukascopy's free 1-minute index CFD prices, bid side, priced like the matching futures contract.</p><p>Every daily series runs on the NYSE calendar, with sessions taken from QQQ's and SPY's own price history. In minute data we first remove placeholder minutes: flat candles where open, high, low and close are equal and volume is zero. We take no entries on days the NYSE was closed.</p></li><li><p><strong>Costs, then more costs.</strong> Every trade pays commission and slippage, the gap between the price you see and the price you get. Then we double and triple them. An edge that dies at twice the cost was never there.</p></li><li><p><strong>The account, not the trade.</strong> A strategy can win most of its trades and still make less money than doing nothing. So we run it as an account and count the days its money sits idle.</p><p><em>Precisely:</em> idle cash earns a Treasury bill rate, credited daily; each issue names the series, usually the 4-week bill. We compare with holding QQQ, the bar, and SPY, the floor, over the same days: total return, dividends included, from each ETF's first trading day where the test allows.</p></li><li><p><strong>Same risk, compared fairly.</strong> A strategy that sits in cash swings less than the index. That makes it look safer, and poorer. So we also compare at equal risk.</p><p><em>Precisely:</em> we run the strategy at a fixed leverage of one, two or three times, or scale it, or the index, to the same volatility, and compare the money at the end. A volatility match uses hindsight, so it is an illustration, not a rule you could trade.</p><p>Borrowed money pays a retail margin rate when positions are held overnight; Issue 05 charged 5.13%. A strategy that is flat by the close every day carries no overnight financing.</p></li><li><p><strong>Alone, and as an add-on.</strong> Some rules are weak alone but help when kept on top of an index holding. We test both.</p><p><em>Precisely:</em> the add-on holds the index with all the money and adds the strategy's trades on top. Any add-on that is positive on average lifts a backtest, even when that average is luck, so it must also pass the luck checks below.</p></li><li><p><strong>Years it never saw.</strong> Most strategies were built on one stretch of history. We split the data into the years a strategy was tuned on and the years it was not, and compare each half with the index in the same half.</p></li><li><p><strong>Next-door settings.</strong> We nudge every parameter. A real edge still works one step either side, in both halves. A lucky setting works at one value only.</p></li><li><p><strong>Delete the clever part.</strong> We rerun the rule without its special filter. If the result stays, the filter was decoration.</p></li><li><p><strong>Count the tries.</strong> Test ten versions and one will look good by chance. We count every version and raise the bar to match.</p><p><em>Precisely:</em> the t-statistic measures how far a result stands out from luck, and 2 is the usual bar. With ten tries, t = 2 becomes about 2.8.</p></li><li><p><strong>Real fills.</strong> A backtest fills the instant a bar closes, and nobody can. We re-price entries from 0 to 300 seconds late. Our own automated orders fill about 47 seconds after the signal.</p><p>Our paper-trading account, which trades without real money, checks the machinery: that orders fill where the backtest says they fill. It cannot prove an edge in a few months, so we never call it a test.</p></li><li><p><strong>The Retail Gate.</strong> Could someone with a day job and an ordinary broker account run it as written? If not, we say what it would take.</p></li><li><p><strong>Numbers from files, checked twice.</strong> A script regenerates every number we publish from stored result files. Nobody types a number into a table. Before anything goes out, a separate check re-derives every headline number. Before we change our test engine, a regression job must reproduce every number we have already published.</p></li></ol><h3>How we compute the figures</h3><ul><li><p>Yearly figures use elapsed calendar time: days divided by 365.25. Never a count of rows.</p></li><li><p>Sharpe ratio: the average daily return in excess of T-bill cash, divided by its sample standard deviation (n &#8722; 1), times the square root of sessions per elapsed year. On the NYSE calendar that is the square root of 252.</p></li><li><p>Precision: we store every result at full precision and round once, when we display it.</p></li></ul><h3>What the verdicts mean</h3><ul><li><p><strong>Fails:</strong> no edge after costs.</p></li><li><p><strong>Loses to the index</strong> (also written &#8220;trails the index&#8221;): the edge is real, but the account trails simply holding QQQ or SPY.</p></li><li><p><strong>Unproven:</strong> the data cannot yet separate a real edge from luck or tuning.</p></li><li><p><strong>Replicates:</strong> the author's claim reproduces on our data.</p></li><li><p><strong>Works as an add-on:</strong> it trails the index alone but helps beside it. We say how strong the evidence is.</p></li><li><p><strong>Data research:</strong> the issue studies data or fills, not a strategy.</p></li></ul><p>On the <a href="https://www.pastperformancelab.com/p/backtested-trading-strategies-vs-buy-and-hold">Scoreboard</a>, each strategy also gets one plain answer to &#8220;should you use it?&#8221;: No, Only as an add-on, Maybe, or Not a strategy (data research).</p><p><strong>Fairness and corrections.</strong> We name and link every author, lead with what replicated and offer a right of reply before publishing. When a published number changes, the post gets a dated &#8220;Updated&#8221; note at the top that says what changed. When a verdict changes, we say so plainly, in the post and on the <a href="https://www.pastperformancelab.com/p/backtested-trading-strategies-vs-buy-and-hold">Scoreboard</a>.</p><p>If you wrote one of these rules and think we got it wrong, write to pastperformancelab@protonmail.com. We print replies in full.</p><p><strong>Disclaimer.</strong> Past Performance Lab discusses how trading strategies behaved on historical data. It is not a financial advisory service, and the author is not a licensed financial adviser. Nothing here is a recommendation to buy, sell or hold any security or to follow any strategy, and nothing is tailored to any reader's circumstances.</p><p>When we test a strategy a reader sends us, we publish the result for everyone; we do not answer individual investment questions. We accept no payment from the authors or products we test. Backtested results are hypothetical, and readers should not rely on this publication in making an investment decision. The same disclaimer is on our <a href="https://www.pastperformancelab.com/about">About page</a>.</p><div class="subscription-widget-wrap-editor" data-attrs="{&quot;url&quot;:&quot;https://www.pastperformancelab.com/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe&quot;,&quot;language&quot;:&quot;en&quot;}" data-component-name="SubscribeWidgetToDOM"><div class="subscription-widget show-subscribe"><div class="preamble"><p class="cta-caption">One strategy tested every Tuesday. Free.</p></div><form class="subscription-widget-subscribe"><input type="email" class="email-input" name="email" placeholder="Type your email&#8230;" tabindex="-1"><input type="submit" class="button primary" value="Subscribe"><div class="fake-input-wrapper"><div class="fake-input"></div><div class="fake-button"></div></div></form></div></div><h3>Your turn</h3><p>Send us the strategy you are about to risk money on. Write to pastperformancelab@protonmail.com.</p><div><hr></div><p><em>Past performance is no guarantee of future results. We check anyway.</em></p><p><em>This is research on historical data, not investment advice. <a href="https://www.pastperformancelab.com/about">Full disclaimer</a>.</em></p>]]></content:encoded></item><item><title><![CDATA[Not a Winner. Maybe a Sidekick.]]></title><description><![CDATA[Twelve fixes for four failed strategies. One breakout came back: it trails QQQ alone and helps beside it, on borderline evidence.]]></description><link>https://www.pastperformancelab.com/p/opening-range-breakout-backtest-gap-filter</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/opening-range-breakout-backtest-gap-filter</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Mon, 21 Sep 2026 01:54:01 GMT</pubDate><enclosure url="https://substackcdn.com/image/fetch/$s_!YVUl!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0be2017a-3029-4bdc-afb6-3de3c4149282_1280x1516.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Issue 08 &#183; September 2026 &#183; 4 strategies &#183; 12 fixes &#183; 13 years of 1-minute data </em></p><p>In Issue 01, four popular strategies failed our tests. We could have left them there. But a failed backtest sometimes hides a decent idea behind one bad rule, so we tried to fix each one before calling it dead.</p><p>We tried twelve fixes. Most did nothing. One brought a strategy back. Then we asked the question that matters for your account: would it have beaten simply owning QQQ?</p><p><strong>One rescue works in the lab. On its own it trails QQQ. Added on top of QQQ it helps, but the evidence is borderline and weakens with every second of delay.</strong><br><em>Method: 1-minute Nasdaq-100 data from October 2013 to August 2026, costs included, account-level returns against QQQ and SPY with dividends.</em></p><div class="captioned-image-container"><figure><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!YVUl!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0be2017a-3029-4bdc-afb6-3de3c4149282_1280x1516.png 424w, https://substackcdn.com/image/fetch/$s_!YVUl!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0be2017a-3029-4bdc-afb6-3de3c4149282_1280x1516.png 848w, https://substackcdn.com/image/fetch/$s_!YVUl!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0be2017a-3029-4bdc-afb6-3de3c4149282_1280x1516.png 1272w, https://substackcdn.com/image/fetch/$s_!YVUl!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0be2017a-3029-4bdc-afb6-3de3c4149282_1280x1516.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!YVUl!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0be2017a-3029-4bdc-afb6-3de3c4149282_1280x1516.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/0be2017a-3029-4bdc-afb6-3de3c4149282_1280x1516.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Table: t-statistic, yearly return, Sharpe ratio, worst drop and verdict for seven strategy versions, with QQQ at 19.4% a year and SPY at 14.2% a year.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: t-statistic, yearly return, Sharpe ratio, worst drop and verdict for seven strategy versions, with QQQ at 19.4% a year and SPY at 14.2% a year." title="Table: t-statistic, yearly return, Sharpe ratio, worst drop and verdict for seven strategy versions, with QQQ at 19.4% a year and SPY at 14.2% a year." srcset="https://substackcdn.com/image/fetch/$s_!YVUl!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0be2017a-3029-4bdc-afb6-3de3c4149282_1280x1516.png 424w, https://substackcdn.com/image/fetch/$s_!YVUl!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0be2017a-3029-4bdc-afb6-3de3c4149282_1280x1516.png 848w, https://substackcdn.com/image/fetch/$s_!YVUl!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0be2017a-3029-4bdc-afb6-3de3c4149282_1280x1516.png 1272w, https://substackcdn.com/image/fetch/$s_!YVUl!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0be2017a-3029-4bdc-afb6-3de3c4149282_1280x1516.png 1456w" sizes="100vw" fetchpriority="high"></picture><div></div></div></div></figure></div><p><strong>01 / THE FIXES</strong></p><h2>Three of the four could not be saved</h2><p><strong>UT Bot.</strong> It flips long and short on an ATR trailing stop. We let it trade only with the 200-day trend. It traded half as often and earned less, because the filter threw out good and bad trades alike.</p><p><strong>Nadaraya-Watson envelope.</strong> It wins most of its trades and still loses money, because its losers are bigger than its winners. The obvious fix is to flip it. Flipped, the average trade is zero after costs: a friction machine in both directions.</p><p><strong>TTM Squeeze.</strong> There was nothing to fix. On 10-minute bars it has no edge to rescue. Use it, if at all, as one input to another signal, not as a strategy.</p><p><strong>02 / THE ONE THAT WORKED</strong></p><h2>Only a gap filter lifted the breakout</h2><p>The 5-minute opening-range breakout is simple. At 9:35 in New York, buy if the first 5-minute candle closed up and sell if it closed down. The stop sits at the other end of that candle, the target is ten times the risk, and anything still open goes at the close.</p><p>As published, it trades every day, and the edge is too thin to tell from luck. We tried ten versions. Filters on the size of the first candle did nothing, and neither did the 200-day trend. One idea worked: trade only on days that open with a gap of at least a fifth of a normal day's range. The average trade more than doubled.</p><div class="captioned-image-container"><figure><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!vi9S!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbc50401c-8854-43c8-8d94-826f1dc95bc6_1280x1148.png 424w, https://substackcdn.com/image/fetch/$s_!vi9S!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbc50401c-8854-43c8-8d94-826f1dc95bc6_1280x1148.png 848w, https://substackcdn.com/image/fetch/$s_!vi9S!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbc50401c-8854-43c8-8d94-826f1dc95bc6_1280x1148.png 1272w, https://substackcdn.com/image/fetch/$s_!vi9S!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbc50401c-8854-43c8-8d94-826f1dc95bc6_1280x1148.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!vi9S!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbc50401c-8854-43c8-8d94-826f1dc95bc6_1280x1148.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/bc50401c-8854-43c8-8d94-826f1dc95bc6_1280x1148.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Horizontal bar chart: t-statistics for eleven versions of the opening-range breakout. Only gap-filter versions clear t = 2, though not every gap setting does; none reaches 2.81.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Horizontal bar chart: t-statistics for eleven versions of the opening-range breakout. Only gap-filter versions clear t = 2, though not every gap setting does; none reaches 2.81." title="Horizontal bar chart: t-statistics for eleven versions of the opening-range breakout. Only gap-filter versions clear t = 2, though not every gap setting does; none reaches 2.81." srcset="https://substackcdn.com/image/fetch/$s_!vi9S!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbc50401c-8854-43c8-8d94-826f1dc95bc6_1280x1148.png 424w, https://substackcdn.com/image/fetch/$s_!vi9S!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbc50401c-8854-43c8-8d94-826f1dc95bc6_1280x1148.png 848w, https://substackcdn.com/image/fetch/$s_!vi9S!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbc50401c-8854-43c8-8d94-826f1dc95bc6_1280x1148.png 1272w, https://substackcdn.com/image/fetch/$s_!vi9S!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbc50401c-8854-43c8-8d94-826f1dc95bc6_1280x1148.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div></figure></div><p>Here is the catch most backtests skip. Try ten versions and one will look good by chance. With ten tries, the bar for "probably not luck" rises from t = 2 to about 2.8. The gap filter reaches 2.7. Close, but not over.</p><p><strong>03 / THE LUCK CHECK</strong></p><h2>It is not one lucky setting</h2><p>A lucky setting works at one value and nowhere near it. This one works across a range: any gap requirement from a tenth to a quarter of a normal day's range lifts the average trade.</p><p>The average trade is also positive in both halves of the data, 2013&#8211;2019 and 2020&#8211;2026. Most of the evidence comes from the second half.</p><div class="captioned-image-container"><figure><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!2p8L!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd3733901-6e66-41ae-afdb-774fb27f76f7_1280x1010.png 424w, https://substackcdn.com/image/fetch/$s_!2p8L!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd3733901-6e66-41ae-afdb-774fb27f76f7_1280x1010.png 848w, https://substackcdn.com/image/fetch/$s_!2p8L!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd3733901-6e66-41ae-afdb-774fb27f76f7_1280x1010.png 1272w, https://substackcdn.com/image/fetch/$s_!2p8L!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd3733901-6e66-41ae-afdb-774fb27f76f7_1280x1010.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!2p8L!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd3733901-6e66-41ae-afdb-774fb27f76f7_1280x1010.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/d3733901-6e66-41ae-afdb-774fb27f76f7_1280x1010.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Line chart: average trade in basis points by gap size required, for 2013&#8211;2019 and 2020&#8211;2026. In both periods the average trade is higher than with no filter for every gap setting from 0.10 to 0.25 ATR.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Line chart: average trade in basis points by gap size required, for 2013&#8211;2019 and 2020&#8211;2026. In both periods the average trade is higher than with no filter for every gap setting from 0.10 to 0.25 ATR." title="Line chart: average trade in basis points by gap size required, for 2013&#8211;2019 and 2020&#8211;2026. In both periods the average trade is higher than with no filter for every gap setting from 0.10 to 0.25 ATR." srcset="https://substackcdn.com/image/fetch/$s_!2p8L!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd3733901-6e66-41ae-afdb-774fb27f76f7_1280x1010.png 424w, https://substackcdn.com/image/fetch/$s_!2p8L!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd3733901-6e66-41ae-afdb-774fb27f76f7_1280x1010.png 848w, https://substackcdn.com/image/fetch/$s_!2p8L!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd3733901-6e66-41ae-afdb-774fb27f76f7_1280x1010.png 1272w, https://substackcdn.com/image/fetch/$s_!2p8L!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd3733901-6e66-41ae-afdb-774fb27f76f7_1280x1010.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div></figure></div><p><strong>04 / THE ACCOUNT</strong></p><h2>Alone it trails QQQ. On top of QQQ it pulls ahead</h2><p>From this issue on, every verdict is measured at the account level against QQQ, the bar, and SPY, the floor: same money, same years, dividends included.</p><p>On its own, the rescued breakout turned $10,000 into a fraction of what either index made. It trades on about three days in five, and a typical trade lasts under half an hour. Meanwhile the account's cash earns T-bill interest.</p><p>But its returns do not move with the Nasdaq. It made money in 2018, when QQQ went nowhere, and in 2022, when QQQ lost a third. So we tested the version a futures trader could run: keep all the cash in QQQ and trade the breakout with futures on top. That account beat QQQ by several points a year, with a smaller worst drop.</p><div class="captioned-image-container"><figure><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!-0Y1!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe56d1bfe-bece-4b58-a435-65f7bfa92667_1280x1166.png 424w, https://substackcdn.com/image/fetch/$s_!-0Y1!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe56d1bfe-bece-4b58-a435-65f7bfa92667_1280x1166.png 848w, https://substackcdn.com/image/fetch/$s_!-0Y1!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe56d1bfe-bece-4b58-a435-65f7bfa92667_1280x1166.png 1272w, https://substackcdn.com/image/fetch/$s_!-0Y1!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe56d1bfe-bece-4b58-a435-65f7bfa92667_1280x1166.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!-0Y1!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe56d1bfe-bece-4b58-a435-65f7bfa92667_1280x1166.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/e56d1bfe-bece-4b58-a435-65f7bfa92667_1280x1166.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Line chart on a log scale: growth of $10,000 in QQQ, SPY, the gap-filtered breakout alone and QQQ with the breakout added on top.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Line chart on a log scale: growth of $10,000 in QQQ, SPY, the gap-filtered breakout alone and QQQ with the breakout added on top." title="Line chart on a log scale: growth of $10,000 in QQQ, SPY, the gap-filtered breakout alone and QQQ with the breakout added on top." srcset="https://substackcdn.com/image/fetch/$s_!-0Y1!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe56d1bfe-bece-4b58-a435-65f7bfa92667_1280x1166.png 424w, https://substackcdn.com/image/fetch/$s_!-0Y1!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe56d1bfe-bece-4b58-a435-65f7bfa92667_1280x1166.png 848w, https://substackcdn.com/image/fetch/$s_!-0Y1!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe56d1bfe-bece-4b58-a435-65f7bfa92667_1280x1166.png 1272w, https://substackcdn.com/image/fetch/$s_!-0Y1!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe56d1bfe-bece-4b58-a435-65f7bfa92667_1280x1166.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div></figure></div><p><strong>05 / THE CATCH</strong></p><h2>The evidence fades before the extra return does</h2><p>Those are best-case numbers: instant fills and one-point costs. Our own automated orders fill about 47 seconds after the signal (Issue 07). At that speed the t-statistic drops to 2.2. At two minutes it is 1.6, and at double costs 1.9.</p><p>The add-on still shows extra return at every speed in the table. That is the trap. Any add-on that is uncorrelated with QQQ and positive on average lifts the backtest, even when that average is luck. The published breakout, the version that failed, would also have "beaten" QQQ as an add-on. What decides it is the evidence, and here the evidence is borderline at best.</p><div class="captioned-image-container"><figure><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!BCfx!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F50a9658e-46bc-4675-90c2-8ae60d813877_1280x1210.png 424w, https://substackcdn.com/image/fetch/$s_!BCfx!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F50a9658e-46bc-4675-90c2-8ae60d813877_1280x1210.png 848w, https://substackcdn.com/image/fetch/$s_!BCfx!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F50a9658e-46bc-4675-90c2-8ae60d813877_1280x1210.png 1272w, https://substackcdn.com/image/fetch/$s_!BCfx!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F50a9658e-46bc-4675-90c2-8ae60d813877_1280x1210.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!BCfx!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F50a9658e-46bc-4675-90c2-8ae60d813877_1280x1210.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/50a9658e-46bc-4675-90c2-8ae60d813877_1280x1210.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Table: the gap-filtered breakout at fill delays from zero to five minutes and at two and three times costs, alone and added to QQQ. At 47 seconds its t-statistic is 2.21.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: the gap-filtered breakout at fill delays from zero to five minutes and at two and three times costs, alone and added to QQQ. At 47 seconds its t-statistic is 2.21." title="Table: the gap-filtered breakout at fill delays from zero to five minutes and at two and three times costs, alone and added to QQQ. At 47 seconds its t-statistic is 2.21." srcset="https://substackcdn.com/image/fetch/$s_!BCfx!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F50a9658e-46bc-4675-90c2-8ae60d813877_1280x1210.png 424w, https://substackcdn.com/image/fetch/$s_!BCfx!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F50a9658e-46bc-4675-90c2-8ae60d813877_1280x1210.png 848w, https://substackcdn.com/image/fetch/$s_!BCfx!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F50a9658e-46bc-4675-90c2-8ae60d813877_1280x1210.png 1272w, https://substackcdn.com/image/fetch/$s_!BCfx!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F50a9658e-46bc-4675-90c2-8ae60d813877_1280x1210.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div></figure></div><h2>The transferable part</h2><ol><li><p><strong>Count your tries.</strong> Ten versions tested means the bar sits near t = 2.8, not 2.</p></li><li><p><strong>Split the years and nudge the setting.</strong> A real filter helps in both halves of the data and at neighbouring values.</p></li><li><p><strong>Test it against QQQ twice: alone and as an add-on.</strong> Then ask whether the add-on's own average survives real fills.</p></li></ol><h2>Your turn</h2><p>Send us the strategy you are about to risk money on. Reply to this email or write to <a href="mailto:pastperformancelab@protonmail.com">pastperformancelab@protonmail.com</a>. We test it and publish what we find.</p><h3>Method</h3><ul><li><p><strong>Data.</strong> Dukascopy 1-minute Nasdaq-100 (US Tech 100) bid prices, 18 October 2013 to 28 August 2026, priced as NQ futures at $20 a point with a 1-point round-trip cost. Signals on the bar close, fills at the next bar's open. Delayed fills are re-priced on the same tape, as in Issue 07.</p></li><li><p><strong>Calendar.</strong> Daily filters (ATR(14), the 200-day average) use NYSE trading days only, and trades on days the US market was closed are excluded. Issue 07 used the tape's own calendar and dollar t-statistics, which gave the gap filter t = 2.60; on NYSE days and percentage returns it is 2.73.</p></li><li><p><strong>Account level.</strong> Each trade controls notional equal to the account. Cash earns the 4-week T-bill rate (FRED) every day. The add-on holds QQQ with all the cash and adds the strategy's trade returns. QQQ and SPY returns include reinvested dividends.</p></li><li><p><strong>Statistics.</strong> t-statistics use per-trade percentage returns. The bar for ten tries is a Bonferroni-adjusted 5% two-sided threshold (t = 2.81).</p></li><li><p><strong>Versions.</strong> UT Bot: a = 3, ATR 10, 10-minute bars, regular hours. Nadaraya-Watson: the non-repainting endpoint estimator, regular hours. TTM Squeeze: 10-minute bars, as in Issue 01.</p></li><li><p><strong>Sources.</strong> 5-minute ORB: Carlo Zarattini and Andrew Aziz, <a href="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4416622">Can Day Trading Really Be Profitable?</a> (2023). <a href="https://www.tradingview.com/script/n8ss8BID-UT-Bot-Alerts">UT Bot Alerts</a> on TradingView. <a href="https://www.tradingview.com/script/Iko0E2kL-Nadaraya-Watson-Envelope-LuxAlgo/">Nadaraya-Watson Envelope [LuxAlgo]</a> on TradingView. TTM Squeeze: John Carter, <em>Mastering the Trade</em>.</p></li></ul><div class="captioned-image-container"><figure><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!8QJN!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feee73869-49ab-43d7-baef-d49e50ac5a48_1280x1562.png 424w, https://substackcdn.com/image/fetch/$s_!8QJN!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feee73869-49ab-43d7-baef-d49e50ac5a48_1280x1562.png 848w, https://substackcdn.com/image/fetch/$s_!8QJN!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feee73869-49ab-43d7-baef-d49e50ac5a48_1280x1562.png 1272w, https://substackcdn.com/image/fetch/$s_!8QJN!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feee73869-49ab-43d7-baef-d49e50ac5a48_1280x1562.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!8QJN!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feee73869-49ab-43d7-baef-d49e50ac5a48_1280x1562.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/eee73869-49ab-43d7-baef-d49e50ac5a48_1280x1562.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Table: trades, win rate, profit factor, t-statistic, average trade, yearly return, Sharpe ratio and maximum drawdown for every version tested.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: trades, win rate, profit factor, t-statistic, average trade, yearly return, Sharpe ratio and maximum drawdown for every version tested." title="Table: trades, win rate, profit factor, t-statistic, average trade, yearly return, Sharpe ratio and maximum drawdown for every version tested." srcset="https://substackcdn.com/image/fetch/$s_!8QJN!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feee73869-49ab-43d7-baef-d49e50ac5a48_1280x1562.png 424w, https://substackcdn.com/image/fetch/$s_!8QJN!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feee73869-49ab-43d7-baef-d49e50ac5a48_1280x1562.png 848w, https://substackcdn.com/image/fetch/$s_!8QJN!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feee73869-49ab-43d7-baef-d49e50ac5a48_1280x1562.png 1272w, https://substackcdn.com/image/fetch/$s_!8QJN!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feee73869-49ab-43d7-baef-d49e50ac5a48_1280x1562.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div></figure></div><p><em>Past performance is no guarantee of future results. We check anyway. This is research, not investment advice.</em></p><div class="subscription-widget-wrap-editor" data-attrs="{&quot;url&quot;:&quot;https://www.pastperformancelab.com/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe&quot;,&quot;language&quot;:&quot;en&quot;}" data-component-name="SubscribeWidgetToDOM"><div class="subscription-widget show-subscribe"><div class="preamble"><p class="cta-caption">Thanks for reading Past Performance! Subscribe for free to receive new posts and support my work.</p></div><form class="subscription-widget-subscribe"><input type="email" class="email-input" name="email" placeholder="Type your email&#8230;" tabindex="-1"><input type="submit" class="button primary" value="Subscribe"><div class="fake-input-wrapper"><div class="fake-input"></div><div class="fake-button"></div></div></form></div></div>]]></content:encoded></item><item><title><![CDATA[The 47-Second Tax]]></title><description><![CDATA[Every backtest fills the instant a bar closes. Real systems cannot. We re-priced three strategies at the speed you can actually trade.]]></description><link>https://www.pastperformancelab.com/p/backtest-vs-live-trading-47-second-delay</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/backtest-vs-live-trading-47-second-delay</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Wed, 16 Sep 2026 13:54:22 GMT</pubDate><enclosure url="https://substackcdn.com/image/fetch/$s_!vPL3!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F463ed310-14b6-421c-ad70-90b47454bac4_1280x562.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Issue 07 &#183; September 2026 &#183; 3 backtests &#183; 7 delays &#183; 2,819 trades re-priced</em></p><p><em>Updated 27 Sep 2026: figures recomputed on the NYSE trading calendar. The verdict is unchanged.</em></p><p>There is one number in every backtest that almost nobody questions: the fill price. The backtest trades at the next bar's open, the instant its signal appears. Nobody trades that fast. Not a person at a screen, and not a retail trading bot.</p><div class="subscription-widget-wrap-editor" data-attrs="{&quot;url&quot;:&quot;https://www.pastperformancelab.com/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe&quot;,&quot;language&quot;:&quot;en&quot;}" data-component-name="SubscribeWidgetToDOM"><div class="subscription-widget show-subscribe"><div class="preamble"><p class="cta-caption">Thanks for reading Past Performance! Subscribe for free to receive new posts and support my work.</p></div><form class="subscription-widget-subscribe"><input type="email" class="email-input" name="email" placeholder="Type your email&#8230;" tabindex="-1"><input type="submit" class="button primary" value="Subscribe"><div class="fake-input-wrapper"><div class="fake-input"></div><div class="fake-button"></div></div></form></div></div><p>So we asked a simple question about three strategies from earlier issues. What happens to them at the speed a real system can actually trade?</p><p><strong>A 47-second delay costs 9&#8211;16% of profit &#183; At two minutes the breakout's edge stops looking real</strong><br><em>Same signals, same trades, same exits. Only the fill time changes.</em></p><p><strong>01 / THE ASSUMPTION</strong></p><h2>The fill that never happens</h2><p>A backtest sees the bar close and fills on the spot. A live system has to wait for its broker to publish that bar, decide, and send the order. On our own automated service the whole trip takes about 47 seconds.</p><div class="captioned-image-container"><figure><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!vPL3!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F463ed310-14b6-421c-ad70-90b47454bac4_1280x562.png 424w, https://substackcdn.com/image/fetch/$s_!vPL3!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F463ed310-14b6-421c-ad70-90b47454bac4_1280x562.png 848w, https://substackcdn.com/image/fetch/$s_!vPL3!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F463ed310-14b6-421c-ad70-90b47454bac4_1280x562.png 1272w, https://substackcdn.com/image/fetch/$s_!vPL3!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F463ed310-14b6-421c-ad70-90b47454bac4_1280x562.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!vPL3!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F463ed310-14b6-421c-ad70-90b47454bac4_1280x562.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/463ed310-14b6-421c-ad70-90b47454bac4_1280x562.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Timeline from a 10-minute bar close to a live fill: about 35 seconds waiting for the broker to publish the bar, then about 12 seconds for the order, filled at about 47 seconds.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Timeline from a 10-minute bar close to a live fill: about 35 seconds waiting for the broker to publish the bar, then about 12 seconds for the order, filled at about 47 seconds." title="Timeline from a 10-minute bar close to a live fill: about 35 seconds waiting for the broker to publish the bar, then about 12 seconds for the order, filled at about 47 seconds." srcset="https://substackcdn.com/image/fetch/$s_!vPL3!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F463ed310-14b6-421c-ad70-90b47454bac4_1280x562.png 424w, https://substackcdn.com/image/fetch/$s_!vPL3!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F463ed310-14b6-421c-ad70-90b47454bac4_1280x562.png 848w, https://substackcdn.com/image/fetch/$s_!vPL3!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F463ed310-14b6-421c-ad70-90b47454bac4_1280x562.png 1272w, https://substackcdn.com/image/fetch/$s_!vPL3!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F463ed310-14b6-421c-ad70-90b47454bac4_1280x562.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div></figure></div><p>Forty-seven seconds sounds harmless. For a strategy that trades momentum, it can be a good part of the move.</p><p><strong>02 / THE TEST</strong></p><h2>Same trades, later fills</h2><p>We changed exactly one thing: the moment each market order fills. The signals, the trades and the exits all stayed where they were. Then we stepped the delay from zero to five minutes and re-priced every order on one-minute data.</p><p><strong>The strategies:</strong> the Saty Phase Oscillator on Nasdaq-100 futures, split into the years it was built on and the years before (Issue 06), and the opening-range breakout with a gap filter, the one strategy from Issue 01 we managed to rescue.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!2GTY!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd2ce8162-799d-4fb6-beda-94719b70bd1b_1280x896.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!2GTY!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd2ce8162-799d-4fb6-beda-94719b70bd1b_1280x896.png 424w, https://substackcdn.com/image/fetch/$s_!2GTY!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd2ce8162-799d-4fb6-beda-94719b70bd1b_1280x896.png 848w, https://substackcdn.com/image/fetch/$s_!2GTY!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd2ce8162-799d-4fb6-beda-94719b70bd1b_1280x896.png 1272w, https://substackcdn.com/image/fetch/$s_!2GTY!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd2ce8162-799d-4fb6-beda-94719b70bd1b_1280x896.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!2GTY!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd2ce8162-799d-4fb6-beda-94719b70bd1b_1280x896.png" width="1280" height="896" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/d2ce8162-799d-4fb6-beda-94719b70bd1b_1280x896.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:896,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:34797,&quot;alt&quot;:&quot;Table: net profit with instant fills versus fills 47 seconds later for two Saty oscillator windows and the opening-range breakout with a gap filter.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: net profit with instant fills versus fills 47 seconds later for two Saty oscillator windows and the opening-range breakout with a gap filter." title="Table: net profit with instant fills versus fills 47 seconds later for two Saty oscillator windows and the opening-range breakout with a gap filter." srcset="https://substackcdn.com/image/fetch/$s_!2GTY!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd2ce8162-799d-4fb6-beda-94719b70bd1b_1280x896.png 424w, https://substackcdn.com/image/fetch/$s_!2GTY!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd2ce8162-799d-4fb6-beda-94719b70bd1b_1280x896.png 848w, https://substackcdn.com/image/fetch/$s_!2GTY!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd2ce8162-799d-4fb6-beda-94719b70bd1b_1280x896.png 1272w, https://substackcdn.com/image/fetch/$s_!2GTY!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd2ce8162-799d-4fb6-beda-94719b70bd1b_1280x896.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p><strong>03 / THE RESULTS</strong></p><h2>Profit leaks, and it leaks early</h2><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!BVH4!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2edc1496-c4f6-4c48-9dff-7e17a3496260_1280x1002.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!BVH4!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2edc1496-c4f6-4c48-9dff-7e17a3496260_1280x1002.png 424w, https://substackcdn.com/image/fetch/$s_!BVH4!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2edc1496-c4f6-4c48-9dff-7e17a3496260_1280x1002.png 848w, https://substackcdn.com/image/fetch/$s_!BVH4!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2edc1496-c4f6-4c48-9dff-7e17a3496260_1280x1002.png 1272w, https://substackcdn.com/image/fetch/$s_!BVH4!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2edc1496-c4f6-4c48-9dff-7e17a3496260_1280x1002.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!BVH4!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2edc1496-c4f6-4c48-9dff-7e17a3496260_1280x1002.png" width="1280" height="1002" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/2edc1496-c4f6-4c48-9dff-7e17a3496260_1280x1002.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1002,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:36037,&quot;alt&quot;:&quot;Line chart: share of instant-fill profit kept at delays from 0 seconds to 5 minutes for three strategies.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Line chart: share of instant-fill profit kept at delays from 0 seconds to 5 minutes for three strategies." title="Line chart: share of instant-fill profit kept at delays from 0 seconds to 5 minutes for three strategies." srcset="https://substackcdn.com/image/fetch/$s_!BVH4!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2edc1496-c4f6-4c48-9dff-7e17a3496260_1280x1002.png 424w, https://substackcdn.com/image/fetch/$s_!BVH4!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2edc1496-c4f6-4c48-9dff-7e17a3496260_1280x1002.png 848w, https://substackcdn.com/image/fetch/$s_!BVH4!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2edc1496-c4f6-4c48-9dff-7e17a3496260_1280x1002.png 1272w, https://substackcdn.com/image/fetch/$s_!BVH4!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2edc1496-c4f6-4c48-9dff-7e17a3496260_1280x1002.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p><em>The out-of-sample Saty line runs almost exactly under the breakout until 47 seconds. Past one minute the Saty figures bounce around: at that horizon the noise is bigger than the effect.</em></p><p>The first fifteen seconds already cost something. By our real delay, every version has given back about a tenth to a sixth of its profit. The breakout keeps sliding from there, and five minutes late most of its profit is gone.</p><blockquote><p>This is not noise. Across all 2,819 trades the cost of waiting is consistent: these strategies trade moves that keep going for about a minute, and a slow system simply buys them later.</p></blockquote><p><strong>04 / THE EDGE</strong></p><h2>When a real edge stops being real</h2><p>Losing some profit is survivable. Losing the evidence is not. The t-statistic tells you whether a result stands out from luck, and 2 is the usual bar.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!ityj!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1d6531f5-d56b-4564-b42e-8edc3bb648b0_1280x1070.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!ityj!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1d6531f5-d56b-4564-b42e-8edc3bb648b0_1280x1070.png 424w, https://substackcdn.com/image/fetch/$s_!ityj!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1d6531f5-d56b-4564-b42e-8edc3bb648b0_1280x1070.png 848w, https://substackcdn.com/image/fetch/$s_!ityj!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1d6531f5-d56b-4564-b42e-8edc3bb648b0_1280x1070.png 1272w, https://substackcdn.com/image/fetch/$s_!ityj!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1d6531f5-d56b-4564-b42e-8edc3bb648b0_1280x1070.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!ityj!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1d6531f5-d56b-4564-b42e-8edc3bb648b0_1280x1070.png" width="1280" height="1070" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/1d6531f5-d56b-4564-b42e-8edc3bb648b0_1280x1070.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1070,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:35468,&quot;alt&quot;:&quot;Line chart: t-statistic of the average trade at delays from 0 seconds to 5 minutes, with a dashed line at t = 2.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Line chart: t-statistic of the average trade at delays from 0 seconds to 5 minutes, with a dashed line at t = 2." title="Line chart: t-statistic of the average trade at delays from 0 seconds to 5 minutes, with a dashed line at t = 2." srcset="https://substackcdn.com/image/fetch/$s_!ityj!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1d6531f5-d56b-4564-b42e-8edc3bb648b0_1280x1070.png 424w, https://substackcdn.com/image/fetch/$s_!ityj!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1d6531f5-d56b-4564-b42e-8edc3bb648b0_1280x1070.png 848w, https://substackcdn.com/image/fetch/$s_!ityj!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1d6531f5-d56b-4564-b42e-8edc3bb648b0_1280x1070.png 1272w, https://substackcdn.com/image/fetch/$s_!ityj!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1d6531f5-d56b-4564-b42e-8edc3bb648b0_1280x1070.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p>The breakout clears that bar with a one-minute delay and fails it at two minutes. The in-sample Saty result survives every delay we tried. The out-of-sample one never cleared the bar, even at zero seconds, which is what Issue 06 was about.</p><p><strong>05 / ON ONE TRADE</strong></p><h2>What the wait looks like in points</h2><div class="captioned-image-container"><figure><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!-1dG!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3a658cd4-809d-46c8-864b-c1ce034fad30_1280x886.png 424w, https://substackcdn.com/image/fetch/$s_!-1dG!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3a658cd4-809d-46c8-864b-c1ce034fad30_1280x886.png 848w, https://substackcdn.com/image/fetch/$s_!-1dG!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3a658cd4-809d-46c8-864b-c1ce034fad30_1280x886.png 1272w, https://substackcdn.com/image/fetch/$s_!-1dG!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3a658cd4-809d-46c8-864b-c1ce034fad30_1280x886.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!-1dG!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3a658cd4-809d-46c8-864b-c1ce034fad30_1280x886.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/3a658cd4-809d-46c8-864b-c1ce034fad30_1280x886.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Table: the cost backtests charge per round trip compared with the average cost and typical price swing of a 47-second wait, in index points.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: the cost backtests charge per round trip compared with the average cost and typical price swing of a 47-second wait, in index points." title="Table: the cost backtests charge per round trip compared with the average cost and typical price swing of a 47-second wait, in index points." srcset="https://substackcdn.com/image/fetch/$s_!-1dG!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3a658cd4-809d-46c8-864b-c1ce034fad30_1280x886.png 424w, https://substackcdn.com/image/fetch/$s_!-1dG!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3a658cd4-809d-46c8-864b-c1ce034fad30_1280x886.png 848w, https://substackcdn.com/image/fetch/$s_!-1dG!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3a658cd4-809d-46c8-864b-c1ce034fad30_1280x886.png 1272w, https://substackcdn.com/image/fetch/$s_!-1dG!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3a658cd4-809d-46c8-864b-c1ce034fad30_1280x886.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div></figure></div><p>Our backtests charge one point per round trip for commissions and slippage. The wait alone swings a round trip by more than twenty times that, in either direction. On average the swing lands against you, at almost four times the cost we charge.</p><p><strong>06 / THE TRANSFERABLE PART</strong></p><h2>Three checks before you trust a backtest</h2><p><strong>Time your own delay.</strong> Measure it on your own setup, from the bar close to the fill. It is never zero.</p><p><strong>Re-price the backtest at that delay.</strong> If your platform cannot, fill at the close of the next one-minute bar instead of its open. It is a crude but honest stand-in for a one-minute delay.</p><p><strong>Prefer edges that survive a minute.</strong> A strategy that only works at zero seconds is a feature of the backtest, not of the market. Or get faster: at 15 seconds, the Saty strategy's delay cost falls to about a third of what it is at 47.</p><p><strong>YOUR TURN</strong></p><h2>Send us the strategy you are about to risk money on</h2><p>Leave a comment with a link to the rules, the video or the paper. We read every one. The strongest go into the testing queue, and each is tested the same way: with costs, at the account level, out of sample and at a realistic delay.</p><h3>Method</h3><p><strong>Data:</strong> Dukascopy one-minute bid prices for the Nasdaq-100, a CFD proxy for NQ futures. One NQ contract at $20 per point, with 1.0 point of round-trip friction on top of every delay.</p><p><strong>Re-pricing:</strong> below 60 seconds, each fill is interpolated inside its one-minute bar. At 60 seconds it is that bar's close. At two and five minutes it is the close of the one-minute bar ending at that time. The breakout's stops and targets are resting orders and stay unchanged.</p><p><strong>Controls:</strong> at zero delay every re-priced entry matches the original backtest, and profits reproduce to the dollar. Interpolation understates the swing inside a minute, so these costs are conservative. The delay cost is statistically solid, with t-statistics between 2.6 and 4.2.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!bR93!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1a8ece79-e614-46ea-a188-ff20867f7840_1280x1242.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!bR93!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1a8ece79-e614-46ea-a188-ff20867f7840_1280x1242.png 424w, https://substackcdn.com/image/fetch/$s_!bR93!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1a8ece79-e614-46ea-a188-ff20867f7840_1280x1242.png 848w, https://substackcdn.com/image/fetch/$s_!bR93!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1a8ece79-e614-46ea-a188-ff20867f7840_1280x1242.png 1272w, https://substackcdn.com/image/fetch/$s_!bR93!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1a8ece79-e614-46ea-a188-ff20867f7840_1280x1242.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!bR93!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1a8ece79-e614-46ea-a188-ff20867f7840_1280x1242.png" width="1280" height="1242" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/1a8ece79-e614-46ea-a188-ff20867f7840_1280x1242.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1242,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:42933,&quot;alt&quot;:&quot;Table: net profit and t-statistic for every delay and strategy.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: net profit and t-statistic for every delay and strategy." title="Table: net profit and t-statistic for every delay and strategy." srcset="https://substackcdn.com/image/fetch/$s_!bR93!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1a8ece79-e614-46ea-a188-ff20867f7840_1280x1242.png 424w, https://substackcdn.com/image/fetch/$s_!bR93!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1a8ece79-e614-46ea-a188-ff20867f7840_1280x1242.png 848w, https://substackcdn.com/image/fetch/$s_!bR93!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1a8ece79-e614-46ea-a188-ff20867f7840_1280x1242.png 1272w, https://substackcdn.com/image/fetch/$s_!bR93!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1a8ece79-e614-46ea-a188-ff20867f7840_1280x1242.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p>Backtested results are hypothetical and do not represent returns any investor achieved. This is research, not investment advice.</p><div class="subscription-widget-wrap-editor" data-attrs="{&quot;url&quot;:&quot;https://www.pastperformancelab.com/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe&quot;,&quot;language&quot;:&quot;en&quot;}" data-component-name="SubscribeWidgetToDOM"><div class="subscription-widget show-subscribe"><div class="preamble"><p class="cta-caption">Thanks for reading Past Performance! Subscribe for free to receive new posts and support my work.</p></div><form class="subscription-widget-subscribe"><input type="email" class="email-input" name="email" placeholder="Type your email&#8230;" tabindex="-1"><input type="submit" class="button primary" value="Subscribe"><div class="fake-input-wrapper"><div class="fake-input"></div><div class="fake-button"></div></div></form></div></div>]]></content:encoded></item><item><title><![CDATA[We Broke Our Own Strategy]]></title><description><![CDATA[The Saty Phase Oscillator beats the index on Sharpe in sample and loses out of sample. The loss rests on two thin data years. Verdict: unproven.]]></description><link>https://www.pastperformancelab.com/p/saty-phase-oscillator-backtest-out-of-sample</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/saty-phase-oscillator-backtest-out-of-sample</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Thu, 03 Sep 2026 09:00:00 GMT</pubDate><enclosure url="https://substack-post-media.s3.amazonaws.com/public/images/1c7a5c3c-02c1-4cce-b3c5-17c0e16febb2_1888x1088.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Issue 06 &#183; 3 September 2026 &#183; Addendum added the same day &#183; 937 trades &#183; 13.6 years</em></p><p><em>Updated 27 Sep 2026: figures recomputed on the NYSE trading calendar with a daily T-bill series. The out-of-sample loss rests on 2013&#8211;14, the thinnest years of the free data; from 2015 the published setting beats buy-and-hold on risk-adjusted return, on too few trades to be sure. Verdict revised to unproven.</em></p><p><em>We spent a week taking other people's backtests apart. Then we pointed the same method at the strategy running live in our own account, and found exactly the flaw we had been criticising in everyone else.</em></p><p><strong>Real in sample &#183; Weak out of sample &#183; Verdict, revised: unproven</strong><br><em>t = 3.31 in sample &#183; t = 1.64 out of sample &#183; from 2015, the published setting beats buy-and-hold on Sharpe (0.89 vs 0.78)</em></p><p><strong>01 / WHY THIS ONE IS DIFFERENT</strong></p><h2>This is the strategy we have money on</h2><p>Every other issue has examined somebody else's work. This one examines ours. The Saty Phase Oscillator is the strategy running in our live paper-trading account right now &#8212; one Nasdaq contract, an entry window between 09:40 and 11:00 New York time, flat by the close. It is the reason the lane exists.</p><p>A reader asked a simple question that we had never asked of it: <strong>is it more profitable than just buying the index?</strong> We had asked that of Connors RSI(2) a day earlier and the answer reversed our verdict. We had never turned it on ourselves.</p><p>Across the full history the answer looked good. 937 trades since January 2013, 55.5% of them winners, and at the account level &#8212; capital in 4-week Treasury bills when flat, buying the index when the signal fires &#8212; it returns 8.61% a year at 6.9% volatility with a worst drawdown of 11.0%. Buying and holding the Nasdaq 100 over the same period returns 19.02% at 20.9% volatility and draws down 35.6%.</p><p>Less money, much less risk. A Sharpe ratio of 0.99 against the index's 0.86. We nearly published that.</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!YdQf!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe8656766-3f51-4696-820b-53866ebff625_1280x1252.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!YdQf!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe8656766-3f51-4696-820b-53866ebff625_1280x1252.png 424w, https://substackcdn.com/image/fetch/$s_!YdQf!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe8656766-3f51-4696-820b-53866ebff625_1280x1252.png 848w, https://substackcdn.com/image/fetch/$s_!YdQf!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe8656766-3f51-4696-820b-53866ebff625_1280x1252.png 1272w, https://substackcdn.com/image/fetch/$s_!YdQf!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe8656766-3f51-4696-820b-53866ebff625_1280x1252.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!YdQf!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe8656766-3f51-4696-820b-53866ebff625_1280x1252.png" width="1280" height="1252" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/e8656766-3f51-4696-820b-53866ebff625_1280x1252.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1252,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:64528,&quot;alt&quot;:&quot;Line chart, log scale: one unit grows to 3.1 times with the Saty oscillator and 10.7 times holding the Nasdaq 100; the strategy's worst drawdown is &#8722;11.0% against &#8722;35.6%.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Line chart, log scale: one unit grows to 3.1 times with the Saty oscillator and 10.7 times holding the Nasdaq 100; the strategy's worst drawdown is &#8722;11.0% against &#8722;35.6%." title="Line chart, log scale: one unit grows to 3.1 times with the Saty oscillator and 10.7 times holding the Nasdaq 100; the strategy's worst drawdown is &#8722;11.0% against &#8722;35.6%." srcset="https://substackcdn.com/image/fetch/$s_!YdQf!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe8656766-3f51-4696-820b-53866ebff625_1280x1252.png 424w, https://substackcdn.com/image/fetch/$s_!YdQf!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe8656766-3f51-4696-820b-53866ebff625_1280x1252.png 848w, https://substackcdn.com/image/fetch/$s_!YdQf!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe8656766-3f51-4696-820b-53866ebff625_1280x1252.png 1272w, https://substackcdn.com/image/fetch/$s_!YdQf!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe8656766-3f51-4696-820b-53866ebff625_1280x1252.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p>Growth of one unit of capital, with the drawdown of each series below. The strategy is in the market on 27% of sessions and in cash the rest of the time, which is what produces the shallow drawdown profile and the shortfall in total return. Both series are gross of tax.</p><p><strong>02 / THE SPLIT</strong></p><h2>Then we cut it in half</h2><p>The strategy was developed on data from December 2018 onward. Everything before that &#8212; January 2013 to November 2018 &#8212; is data it never saw. That is a genuine out-of-sample window, and it is the first thing we check on anyone else's work.</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!1KjX!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2dcc3c4a-9801-4202-8aff-7b0d81594bc5_1280x752.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!1KjX!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2dcc3c4a-9801-4202-8aff-7b0d81594bc5_1280x752.png 424w, https://substackcdn.com/image/fetch/$s_!1KjX!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2dcc3c4a-9801-4202-8aff-7b0d81594bc5_1280x752.png 848w, https://substackcdn.com/image/fetch/$s_!1KjX!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2dcc3c4a-9801-4202-8aff-7b0d81594bc5_1280x752.png 1272w, https://substackcdn.com/image/fetch/$s_!1KjX!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2dcc3c4a-9801-4202-8aff-7b0d81594bc5_1280x752.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!1KjX!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2dcc3c4a-9801-4202-8aff-7b0d81594bc5_1280x752.png" width="1280" height="752" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/2dcc3c4a-9801-4202-8aff-7b0d81594bc5_1280x752.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:752,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:35043,&quot;alt&quot;:&quot;Table: out of sample, 2013/01 &#8211; 2018/11. Saty makes 4.27% a year at Sharpe 0.67; the Nasdaq 100 makes 17.11% at 1.06.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: out of sample, 2013/01 &#8211; 2018/11. Saty makes 4.27% a year at Sharpe 0.67; the Nasdaq 100 makes 17.11% at 1.06." title="Table: out of sample, 2013/01 &#8211; 2018/11. Saty makes 4.27% a year at Sharpe 0.67; the Nasdaq 100 makes 17.11% at 1.06." srcset="https://substackcdn.com/image/fetch/$s_!1KjX!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2dcc3c4a-9801-4202-8aff-7b0d81594bc5_1280x752.png 424w, https://substackcdn.com/image/fetch/$s_!1KjX!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2dcc3c4a-9801-4202-8aff-7b0d81594bc5_1280x752.png 848w, https://substackcdn.com/image/fetch/$s_!1KjX!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2dcc3c4a-9801-4202-8aff-7b0d81594bc5_1280x752.png 1272w, https://substackcdn.com/image/fetch/$s_!1KjX!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2dcc3c4a-9801-4202-8aff-7b0d81594bc5_1280x752.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!2on8!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F28282b3d-8e5a-4fe2-8753-e256030b0eae_1280x710.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!2on8!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F28282b3d-8e5a-4fe2-8753-e256030b0eae_1280x710.png 424w, https://substackcdn.com/image/fetch/$s_!2on8!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F28282b3d-8e5a-4fe2-8753-e256030b0eae_1280x710.png 848w, https://substackcdn.com/image/fetch/$s_!2on8!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F28282b3d-8e5a-4fe2-8753-e256030b0eae_1280x710.png 1272w, https://substackcdn.com/image/fetch/$s_!2on8!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F28282b3d-8e5a-4fe2-8753-e256030b0eae_1280x710.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!2on8!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F28282b3d-8e5a-4fe2-8753-e256030b0eae_1280x710.png" width="1280" height="710" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/28282b3d-8e5a-4fe2-8753-e256030b0eae_1280x710.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:710,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:34533,&quot;alt&quot;:&quot;Table: in sample, 2018/12 &#8211; 2026/08. Saty makes 12.06% a year at Sharpe 1.19; the Nasdaq 100 makes 20.52% at 0.79.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: in sample, 2018/12 &#8211; 2026/08. Saty makes 12.06% a year at Sharpe 1.19; the Nasdaq 100 makes 20.52% at 0.79." title="Table: in sample, 2018/12 &#8211; 2026/08. Saty makes 12.06% a year at Sharpe 1.19; the Nasdaq 100 makes 20.52% at 0.79." srcset="https://substackcdn.com/image/fetch/$s_!2on8!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F28282b3d-8e5a-4fe2-8753-e256030b0eae_1280x710.png 424w, https://substackcdn.com/image/fetch/$s_!2on8!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F28282b3d-8e5a-4fe2-8753-e256030b0eae_1280x710.png 848w, https://substackcdn.com/image/fetch/$s_!2on8!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F28282b3d-8e5a-4fe2-8753-e256030b0eae_1280x710.png 1272w, https://substackcdn.com/image/fetch/$s_!2on8!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F28282b3d-8e5a-4fe2-8753-e256030b0eae_1280x710.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><blockquote><p><strong>The average trade is about 3 times larger in the window the strategy was built in.</strong> +0.148% against +0.050%.</p></blockquote><p>Win rate 58.5% in sample against 52.7% out. Per-trade-day t-statistic 3.31 against 1.64, which is not significant at any conventional threshold. Out of sample the top five trade days account for 47% of all profit &#8212; the same concentration that failed the opening range breakout in our first batch.</p><p>And the direction of the comparison flips. In sample, Saty beats the index on Sharpe by a wide margin, 1.19 to 0.79. Out of sample it loses, 0.67 to 1.06. The full-history figure that looked like a win is the average of a strong half and a weak half.</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!Or2P!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff3fcfdc1-fc8f-48c9-9b04-0de4c5a0dda9_1280x1066.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!Or2P!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff3fcfdc1-fc8f-48c9-9b04-0de4c5a0dda9_1280x1066.png 424w, https://substackcdn.com/image/fetch/$s_!Or2P!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff3fcfdc1-fc8f-48c9-9b04-0de4c5a0dda9_1280x1066.png 848w, https://substackcdn.com/image/fetch/$s_!Or2P!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff3fcfdc1-fc8f-48c9-9b04-0de4c5a0dda9_1280x1066.png 1272w, https://substackcdn.com/image/fetch/$s_!Or2P!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff3fcfdc1-fc8f-48c9-9b04-0de4c5a0dda9_1280x1066.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!Or2P!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff3fcfdc1-fc8f-48c9-9b04-0de4c5a0dda9_1280x1066.png" width="1280" height="1066" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/f3fcfdc1-fc8f-48c9-9b04-0de4c5a0dda9_1280x1066.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1066,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:71546,&quot;alt&quot;:&quot;Heat map: monthly account returns of the Saty oscillator by year, with the year total, the Nasdaq 100 benchmark, the worst drawdown and the Sharpe ratio for each year.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Heat map: monthly account returns of the Saty oscillator by year, with the year total, the Nasdaq 100 benchmark, the worst drawdown and the Sharpe ratio for each year." title="Heat map: monthly account returns of the Saty oscillator by year, with the year total, the Nasdaq 100 benchmark, the worst drawdown and the Sharpe ratio for each year." srcset="https://substackcdn.com/image/fetch/$s_!Or2P!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff3fcfdc1-fc8f-48c9-9b04-0de4c5a0dda9_1280x1066.png 424w, https://substackcdn.com/image/fetch/$s_!Or2P!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff3fcfdc1-fc8f-48c9-9b04-0de4c5a0dda9_1280x1066.png 848w, https://substackcdn.com/image/fetch/$s_!Or2P!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff3fcfdc1-fc8f-48c9-9b04-0de4c5a0dda9_1280x1066.png 1272w, https://substackcdn.com/image/fetch/$s_!Or2P!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff3fcfdc1-fc8f-48c9-9b04-0de4c5a0dda9_1280x1066.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p>Green is a positive month, red negative, intensity scaled to magnitude. The Bench column is the Nasdaq 100 over the same year. The pre-2019 rows are the out-of-sample period: mostly positive, consistently small, and consistently behind an index that was compounding at 17% a year with a 1.06 Sharpe.</p><p><strong>03 / THE COUNTER-ARGUMENT</strong></p><h2>The case that this is regime, not overfitting</h2><p>We want to put this as strongly as the finding, because we think it is genuinely unresolved and because we would demand the same fairness if we were the ones being examined.</p><p>2013 to 2018 was an extraordinarily smooth Nasdaq melt-up. Buying and holding posted a 1.06 Sharpe ratio over those six years, which is an exceptional number for an equity index and a brutal benchmark for anything defensive. 2018 to 2026 contained the COVID crash and the 2022 bear market, and buy-and-hold's Sharpe fell to 0.79 while Saty's shallow-drawdown profile did exactly what it is designed to do.</p><p>A defensive intraday strategy <em>should</em> look bad against a melt-up and good against a decade with two crashes in it. That pattern is what you would expect from a real strategy running through different weather, and it is also what you would expect from an overfitted one. The two explanations predict the same data.</p><p>459 out-of-sample trade days at a t-statistic of 1.64 cannot separate them. That is the honest state of knowledge, and anyone who tells you they can resolve it from this sample is selling something.</p><p><em>Update: the split alone cannot separate them. The addendum below tries the parameter neighbourhood, then looks again at the data behind the weak half.</em></p><p><strong>ADDENDUM &#183; SAME DAY</strong></p><h2>The test we said we could not run</h2><p>A few hours after publishing, we found the test. Section 03 says 459 out-of-sample trade days cannot separate regime from overfitting, and that is true of the split on its own. The parameter neighbourhood can help, and we owe it to you to show it.</p><p>The strategy enters when its oscillator crosses &#177;100. We re-ran it at every threshold from 50 to 150 in steps of ten, in both windows, at the account level, against the same buy-and-hold benchmark. The logic is simple. <strong>If the in-sample advantage were regime, every threshold should show it.</strong> If it were parameter selection, 100 should sit on a peak that the out-of-sample window does not share.</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!DMP2!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbd199a23-b355-4850-b5b1-18b9ec844287_1280x1046.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!DMP2!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbd199a23-b355-4850-b5b1-18b9ec844287_1280x1046.png 424w, https://substackcdn.com/image/fetch/$s_!DMP2!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbd199a23-b355-4850-b5b1-18b9ec844287_1280x1046.png 848w, https://substackcdn.com/image/fetch/$s_!DMP2!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbd199a23-b355-4850-b5b1-18b9ec844287_1280x1046.png 1272w, https://substackcdn.com/image/fetch/$s_!DMP2!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbd199a23-b355-4850-b5b1-18b9ec844287_1280x1046.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!DMP2!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbd199a23-b355-4850-b5b1-18b9ec844287_1280x1046.png" width="1280" height="1046" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/bd199a23-b355-4850-b5b1-18b9ec844287_1280x1046.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1046,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:38702,&quot;alt&quot;:&quot;Line chart: account Sharpe ratio by entry threshold. In sample the peak is at 100 (1.18); out of sample the best is 140 (0.87) against buy-and-hold 1.06.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Line chart: account Sharpe ratio by entry threshold. In sample the peak is at 100 (1.18); out of sample the best is 140 (0.87) against buy-and-hold 1.06." title="Line chart: account Sharpe ratio by entry threshold. In sample the peak is at 100 (1.18); out of sample the best is 140 (0.87) against buy-and-hold 1.06." srcset="https://substackcdn.com/image/fetch/$s_!DMP2!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbd199a23-b355-4850-b5b1-18b9ec844287_1280x1046.png 424w, https://substackcdn.com/image/fetch/$s_!DMP2!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbd199a23-b355-4850-b5b1-18b9ec844287_1280x1046.png 848w, https://substackcdn.com/image/fetch/$s_!DMP2!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbd199a23-b355-4850-b5b1-18b9ec844287_1280x1046.png 1272w, https://substackcdn.com/image/fetch/$s_!DMP2!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbd199a23-b355-4850-b5b1-18b9ec844287_1280x1046.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p>Fixed calendar windows: 2013-01 to 2018-11 and 2018-12 to 2026-08. Cells at 130 to 150 hold fewer than 200 trades each and are too thin to read on their own.</p><p>In sample, 100 is the peak of a hump that runs from 90 to 120: 0.68 at 80, 0.96 at 90, 1.18 at 100, 1.08 at 110, 0.88 at 120. The published figure is the best of the eleven thresholds we tested. Out of sample there is no peak at 100. The best threshold is 140 and no threshold reaches buy-and-hold's 1.06.</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!FZTn!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F45dac3dc-c459-465b-a226-ccae5846b034_1280x1266.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!FZTn!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F45dac3dc-c459-465b-a226-ccae5846b034_1280x1266.png 424w, https://substackcdn.com/image/fetch/$s_!FZTn!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F45dac3dc-c459-465b-a226-ccae5846b034_1280x1266.png 848w, https://substackcdn.com/image/fetch/$s_!FZTn!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F45dac3dc-c459-465b-a226-ccae5846b034_1280x1266.png 1272w, https://substackcdn.com/image/fetch/$s_!FZTn!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F45dac3dc-c459-465b-a226-ccae5846b034_1280x1266.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!FZTn!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F45dac3dc-c459-465b-a226-ccae5846b034_1280x1266.png" width="1280" height="1266" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/45dac3dc-c459-465b-a226-ccae5846b034_1280x1266.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1266,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:45139,&quot;alt&quot;:&quot;Table: trades, per-trade t-statistic and account Sharpe for thresholds 50 to 150, out of sample (2013&#8211;2018) and in sample (2018&#8211;2026).&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: trades, per-trade t-statistic and account Sharpe for thresholds 50 to 150, out of sample (2013&#8211;2018) and in sample (2018&#8211;2026)." title="Table: trades, per-trade t-statistic and account Sharpe for thresholds 50 to 150, out of sample (2013&#8211;2018) and in sample (2018&#8211;2026)." srcset="https://substackcdn.com/image/fetch/$s_!FZTn!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F45dac3dc-c459-465b-a226-ccae5846b034_1280x1266.png 424w, https://substackcdn.com/image/fetch/$s_!FZTn!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F45dac3dc-c459-465b-a226-ccae5846b034_1280x1266.png 848w, https://substackcdn.com/image/fetch/$s_!FZTn!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F45dac3dc-c459-465b-a226-ccae5846b034_1280x1266.png 1272w, https://substackcdn.com/image/fetch/$s_!FZTn!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F45dac3dc-c459-465b-a226-ccae5846b034_1280x1266.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p>Then the walk-forward, which is the only fair way to choose a parameter. Pick the threshold on 2013 to 2018 without looking at what came after and you pick 140. Run it on 2018 to 2026 and you get a Sharpe of 0.77 against buy-and-hold's 0.79, at a fraction of the return (5.6% a year against 20.5%), on 134 trades in eight years. Pick on 2018 to 2026 and you pick 100, which then loses 0.67 to 1.06. On this split, neither direction beats the index.</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!UXDO!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5629b672-ddbf-4fad-a113-6ac1c2fa707f_1280x578.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!UXDO!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5629b672-ddbf-4fad-a113-6ac1c2fa707f_1280x578.png 424w, https://substackcdn.com/image/fetch/$s_!UXDO!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5629b672-ddbf-4fad-a113-6ac1c2fa707f_1280x578.png 848w, https://substackcdn.com/image/fetch/$s_!UXDO!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5629b672-ddbf-4fad-a113-6ac1c2fa707f_1280x578.png 1272w, https://substackcdn.com/image/fetch/$s_!UXDO!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5629b672-ddbf-4fad-a113-6ac1c2fa707f_1280x578.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!UXDO!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5629b672-ddbf-4fad-a113-6ac1c2fa707f_1280x578.png" width="1280" height="578" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/5629b672-ddbf-4fad-a113-6ac1c2fa707f_1280x578.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:578,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:25381,&quot;alt&quot;:&quot;Table: chosen on 2013&#8211;2018 the best threshold is 140, scoring Sharpe 0.77 against 0.79; chosen on 2018&#8211;2026 it is 100, scoring 0.67 against 1.06.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: chosen on 2013&#8211;2018 the best threshold is 140, scoring Sharpe 0.77 against 0.79; chosen on 2018&#8211;2026 it is 100, scoring 0.67 against 1.06." title="Table: chosen on 2013&#8211;2018 the best threshold is 140, scoring Sharpe 0.77 against 0.79; chosen on 2018&#8211;2026 it is 100, scoring 0.67 against 1.06." srcset="https://substackcdn.com/image/fetch/$s_!UXDO!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5629b672-ddbf-4fad-a113-6ac1c2fa707f_1280x578.png 424w, https://substackcdn.com/image/fetch/$s_!UXDO!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5629b672-ddbf-4fad-a113-6ac1c2fa707f_1280x578.png 848w, https://substackcdn.com/image/fetch/$s_!UXDO!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5629b672-ddbf-4fad-a113-6ac1c2fa707f_1280x578.png 1272w, https://substackcdn.com/image/fetch/$s_!UXDO!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5629b672-ddbf-4fad-a113-6ac1c2fa707f_1280x578.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><blockquote><p>Trades entered between 100 and 110 on the oscillator earned $554 each in the window the threshold was chosen in, and $5 each outside it.</p></blockquote><p>Regime is real, and we are not withdrawing section 03. At every readable threshold the average trade is larger after 2018, and about 1.6&#215; of that is simply the volatility difference between the two periods (24.2% against 15.5%). But regime lifts the whole family a little. It does not explain why one threshold, the one we chose, beats its neighbours by so much in the window we chose it in.</p><p><strong>Then we looked at the data behind the weak half.</strong> The out-of-sample loss rests on 2013 and 2014, the thinnest years of the free data; Issue 09 (Tuesday 29 September) shows why. Start the out-of-sample window in January 2015 and threshold 100 is the best of the eleven, with a Sharpe of 0.89 against buy-and-hold's 0.78. Walk-forward now picks 100 in both directions. But that rests on 262 trades at a t-statistic of 1.76, and it earns 6.0% a year against the index's 13.2%.</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!5nT9!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3e81cfac-ab21-4b7b-83a2-50d71983fb04_1280x1338.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!5nT9!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3e81cfac-ab21-4b7b-83a2-50d71983fb04_1280x1338.png 424w, https://substackcdn.com/image/fetch/$s_!5nT9!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3e81cfac-ab21-4b7b-83a2-50d71983fb04_1280x1338.png 848w, https://substackcdn.com/image/fetch/$s_!5nT9!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3e81cfac-ab21-4b7b-83a2-50d71983fb04_1280x1338.png 1272w, https://substackcdn.com/image/fetch/$s_!5nT9!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3e81cfac-ab21-4b7b-83a2-50d71983fb04_1280x1338.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!5nT9!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3e81cfac-ab21-4b7b-83a2-50d71983fb04_1280x1338.png" width="1280" height="1338" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/3e81cfac-ab21-4b7b-83a2-50d71983fb04_1280x1338.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1338,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:51220,&quot;alt&quot;:&quot;Table: out of sample from 2015 to 2018, threshold 100 makes 6.0% a year at Sharpe 0.89 against buy-and-hold 13.2% at 0.78, on 262 trades with t 1.76.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: out of sample from 2015 to 2018, threshold 100 makes 6.0% a year at Sharpe 0.89 against buy-and-hold 13.2% at 0.78, on 262 trades with t 1.76." title="Table: out of sample from 2015 to 2018, threshold 100 makes 6.0% a year at Sharpe 0.89 against buy-and-hold 13.2% at 0.78, on 262 trades with t 1.76." srcset="https://substackcdn.com/image/fetch/$s_!5nT9!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3e81cfac-ab21-4b7b-83a2-50d71983fb04_1280x1338.png 424w, https://substackcdn.com/image/fetch/$s_!5nT9!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3e81cfac-ab21-4b7b-83a2-50d71983fb04_1280x1338.png 848w, https://substackcdn.com/image/fetch/$s_!5nT9!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3e81cfac-ab21-4b7b-83a2-50d71983fb04_1280x1338.png 1272w, https://substackcdn.com/image/fetch/$s_!5nT9!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3e81cfac-ab21-4b7b-83a2-50d71983fb04_1280x1338.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p>So the verdict changes again, toward caution. Not "fails", not "works": <strong>unproven</strong>. The paper lane keeps running at 100, because re-tuning it on this test would be the exact sin the test describes, and its job was never validation. And the parameter neighbourhood in both windows stays a standard gate here, applied to everyone we examine, before any in-versus-out-of-sample claim is published.</p><p><strong>04 / THE ARITHMETIC OF WAITING</strong></p><h2>What six months of live trading can and cannot prove</h2><p>The obvious answer is to run it forward and find out. We looked at what that would actually deliver, and the answer is sobering.</p><p>The signal fires on 27% of sessions &#8212; about 69 trades a year, a median of 5 a month, and across 164 months of history there has never been a month with zero trades. So the lane is healthy; a couple of quiet sessions means nothing. A six-month run contains a median of 31 trades, ranging from 20 in the quietest stretch to 92 in the busiest.</p><p>Now the problem. 31 trades at a 55% win rate has a standard deviation of 2.8 wins. Two standard deviations either side puts the observed win rate anywhere between 38% and 73% on luck alone. A six-month paper run cannot distinguish a working strategy from a broken one. It cannot even distinguish either from a coin.</p><p>So we are changing what we claim the lane is for. It is not validating the edge, because it mathematically cannot. It is proving the machinery &#8212; that orders fill where the backtest says they fill, that the entry window is respected, that positions flatten &#8212; and it is accumulating forward out-of-sample evidence that will be worth something in three years and nothing in six months. We will keep running it, and we will stop describing it as a test.</p><p><strong>05 / THE TRANSFERABLE PART</strong></p><h2>The test you should run on us</h2><p>Three questions, and they are the ones we now apply to everything including ourselves.</p><p><strong>Where does the sample end and the tuning begin?</strong> Almost every published strategy has a window in which it was developed. Ask which one it is, then ask to see the result outside it. If the author cannot tell you where that boundary sits, the whole result is in sample.</p><p><strong>What did the benchmark do in each half?</strong> A strategy that beats a 0.79-Sharpe market and loses to a 1.06-Sharpe market has told you something about itself, but not what the headline says. Compare within each regime, not across the average.</p><p><strong>How many trades would it take to know?</strong> Run the arithmetic before you run the strategy. If the sample you are going to collect cannot separate the hypotheses, waiting is not evidence-gathering, it is just waiting.</p><p>We are not retiring this strategy. It has a real and statistically strong result in one half of its history, a weak but positive one in the other, and a defensive profile that is genuinely useful. What it does not have is proof that it beats holding the index, and we are not going to write that it does. The addendum sharpens this: the weak half rests on the two thinnest years of the data, and without them the published setting holds up, on too few trades to be sure.</p><h3>Method</h3><p>Data: Dukascopy 1-minute bid, resampled to 10-minute bars on NYSE trading sessions only. 3,429 sessions, 2013-01-03 to 2026-08-21. Signal computed on bar close, filled at the next bar's open, flat at 16:00 New York. Friction one index point per round trip.</p><p>Account construction: each trade expressed as a percent of the notional it controlled at entry (index level &#215; $20 per Nasdaq point), compounded daily, with idle capital earning the daily 4-week T-bill rate. Annual figures use calendar years. Benchmark is the return of holding the index over the identical sessions.</p><p>On leverage: the 3&#215; rows are priced without a borrowing charge, which is defensible only because this strategy is flat by the close every day &#8212; there is no overnight financing, and futures embed the risk-free rate in the basis. A cash-equity strategy carrying positions overnight would need the real margin rate charged against it, and when we did that to Connors RSI(2) it destroyed the edge. Worst single day at 1&#215; is &#8722;5.45% of notional, so &#8722;16.4% at 3&#215;.</p><p>Addendum: eleven thresholds, 50 to 150 in steps of ten, each window run on its own with the first 200 bars skipped, fixed calendar windows 2013-01-01 to 2018-12-01 and 2018-12-01 to 2026-09-01. At 100 the sweep applies the same rules as sections 01 and 02, but it counts trades rather than trade days (465 against 459 out of sample) and its windows differ by a few days at the edges, so its figures can differ in the second decimal. Walk-forward chooses the threshold by Sharpe on one window and scores it on the other. Robustness window: 2015-01-01 to 2018-12-01, same construction.</p><p>Backtested results are hypothetical and do not represent returns any investor achieved. This is research, not investment advice.</p>]]></content:encoded></item><item><title><![CDATA[The Winner That Doesn't Win]]></title><description><![CDATA[Connors RSI(2) has a real edge and wins 73% of its trades. It still earns 4.47% a year against buy-and-hold's 12.71%.]]></description><link>https://www.pastperformancelab.com/p/connors-rsi-2-backtest-vs-buy-and-hold</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/connors-rsi-2-backtest-vs-buy-and-hold</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Wed, 02 Sep 2026 17:00:00 GMT</pubDate><enclosure url="https://substack-post-media.s3.amazonaws.com/public/images/63d96456-5593-4fa1-a3af-d59a63e602a8_1888x984.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Strategy Verification &#183; Issue 05 &#183; 2 September 2026 &#183; US500 daily, 13.4 years</em></p><p><em>Updated 27 Sep 2026: annual figures recomputed on the NYSE trading calendar with a daily T-bill series. The verdict is unchanged. The flat era moves from 2020&#8211;2022 to 2017&#8211;2019, and the slower-exit version (RSI(2) below 15, exit above the 10-day average) no longer improves on the original, so we withdrew it.</em></p><p><em>Connors RSI(2) was the one strategy in our first batch of five that survived. It passes every statistical gate we can throw at it. Then you put it in an account and it loses to buying the index and going to sleep.</em></p><p><strong>Edge is real &#183; Loses to buy-and-hold &#183; Works as an overlay</strong><br><em>t = 3.04 &#183; but 4.47%/yr against the index's 12.71% &#183; invested 11% of the time</em></p><p><strong>01 / THE RULES</strong></p><h2>Five lines, and you can check them on a phone</h2><p>Larry Connors published this in <em>Short Term Trading Strategies That Work</em> and it has been reposted, repackaged and resold ever since. It is the simplest thing we have tested. It is also the only survivor of our first batch, where the 5-minute opening range breakout, UT Bot, TTM Squeeze and the Nadaraya-Watson envelope all failed.</p><h3>Connors RSI(2) &#8212; as published, as tested</h3><p><strong>Universe.</strong> One broad index. We tested the S&amp;P 500 and, separately, the Nasdaq 100.</p><p><strong>Filter.</strong> Only take trades when <code>close &gt; SMA(200)</code> &#8212; long-term uptrend only.</p><p><strong>Entry.</strong> Buy when <code>RSI(2) &lt; 10</code>. A two-period RSI hits single digits after a sharp two- or three-day drop.</p><p><strong>Exit.</strong> Sell when <code>close &gt; SMA(5)</code>. Typically five days later.</p><p><strong>Direction.</strong> Long only. No shorts, no options, no stop-loss.</p><p>Over 3,365 NYSE sessions from April 2013 to August 2026 that produces 108 trades, a 73.1% win rate, a profit factor of 2.13 after costs and a t-statistic of 3.04 on per-trade returns. By the standards of what circulates online, that is an unusually solid result. We spent the rest of the day trying to break it.</p><p><strong>02 / THE GATES</strong></p><h2>Four ways it could have died, and didn't</h2><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!mGyg!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd74c9ee3-4c36-4199-bc24-e0157a9c35c0_1280x1484.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!mGyg!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd74c9ee3-4c36-4199-bc24-e0157a9c35c0_1280x1484.png 424w, https://substackcdn.com/image/fetch/$s_!mGyg!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd74c9ee3-4c36-4199-bc24-e0157a9c35c0_1280x1484.png 848w, https://substackcdn.com/image/fetch/$s_!mGyg!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd74c9ee3-4c36-4199-bc24-e0157a9c35c0_1280x1484.png 1272w, https://substackcdn.com/image/fetch/$s_!mGyg!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd74c9ee3-4c36-4199-bc24-e0157a9c35c0_1280x1484.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!mGyg!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd74c9ee3-4c36-4199-bc24-e0157a9c35c0_1280x1484.png" width="1280" height="1484" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/d74c9ee3-4c36-4199-bc24-e0157a9c35c0_1280x1484.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1484,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:58121,&quot;alt&quot;:&quot;Table: per-trade results by era, by fill timing and on the Nasdaq 100. At the signal close: 108 trades, profit factor 2.13, t 3.04; at the next open, t 2.75.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: per-trade results by era, by fill timing and on the Nasdaq 100. At the signal close: 108 trades, profit factor 2.13, t 3.04; at the next open, t 2.75." title="Table: per-trade results by era, by fill timing and on the Nasdaq 100. At the signal close: 108 trades, profit factor 2.13, t 3.04; at the next open, t 2.75." srcset="https://substackcdn.com/image/fetch/$s_!mGyg!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd74c9ee3-4c36-4199-bc24-e0157a9c35c0_1280x1484.png 424w, https://substackcdn.com/image/fetch/$s_!mGyg!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd74c9ee3-4c36-4199-bc24-e0157a9c35c0_1280x1484.png 848w, https://substackcdn.com/image/fetch/$s_!mGyg!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd74c9ee3-4c36-4199-bc24-e0157a9c35c0_1280x1484.png 1272w, https://substackcdn.com/image/fetch/$s_!mGyg!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd74c9ee3-4c36-4199-bc24-e0157a9c35c0_1280x1484.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p><strong>It has a dead patch.</strong> From 2017 to 2019 the edge went to nothing: 22 trades, profit factor 1.01, t of 0.02. Then 2020 to 2022 was weak (19 trades, t 0.74). Anyone running this needs to know that in advance, because three flat years is exactly how long it takes to abandon a system right before it starts working again. 2023 to 2026 is the strongest era in the record.</p><p><strong>You do not need to trade the close.</strong> This is the finding that matters most for anyone with a job. Connors' rules assume you buy at the close of the signal day. Place the order for the next session's open instead and the profit factor falls from 2.13 to 1.99: the average trade shrinks by about 14%, and the t-statistic stays well above 2. In the 2023&#8211;2026 era the close fill does better (profit factor 4.35 against 3.11), but the evening order still clears every gate. You can run this with an order placed the night before.</p><p><strong>It is a plateau, not a knife-edge.</strong> Every entry threshold from 5 to 20 keeps the t-statistic above 2.2. RSI(3) still works; RSI(4) fires only 13 times, too few to read. The 200-day filter can be a 100-day filter. One change does not survive: a slower exit, above the 10-day average instead of the 5-day, drops the t-statistic to 1.11.</p><p><strong>03 / THE REVERSAL</strong></p><h2>Now put it in an account</h2><p>Everything above is a per-trade statistic. A per-trade statistic tells you how good the trades are. It does not tell you how good the account is &#8212; and for a strategy that is invested 10.8% of the time, those are not the same question.</p><p>So we ran the account. Capital sits in 4-week T-bills when flat, buys the index at the open when the signal fires, sells at the open when the exit fires, pays three basis points a round trip. This is the number that would actually have appeared on a statement.</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!TkgZ!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27b52f51-7baf-418f-8ba0-5f0db8a6310b_1280x906.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!TkgZ!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27b52f51-7baf-418f-8ba0-5f0db8a6310b_1280x906.png 424w, https://substackcdn.com/image/fetch/$s_!TkgZ!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27b52f51-7baf-418f-8ba0-5f0db8a6310b_1280x906.png 848w, https://substackcdn.com/image/fetch/$s_!TkgZ!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27b52f51-7baf-418f-8ba0-5f0db8a6310b_1280x906.png 1272w, https://substackcdn.com/image/fetch/$s_!TkgZ!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27b52f51-7baf-418f-8ba0-5f0db8a6310b_1280x906.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!TkgZ!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27b52f51-7baf-418f-8ba0-5f0db8a6310b_1280x906.png" width="1280" height="906" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/27b52f51-7baf-418f-8ba0-5f0db8a6310b_1280x906.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:906,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:40564,&quot;alt&quot;:&quot;Table: Connors RSI(2) at the account level makes 4.47% a year against 12.71% for buy and hold; Sharpe 0.49 against 0.72; final multiple 1.79 against 4.95.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: Connors RSI(2) at the account level makes 4.47% a year against 12.71% for buy and hold; Sharpe 0.49 against 0.72; final multiple 1.79 against 4.95." title="Table: Connors RSI(2) at the account level makes 4.47% a year against 12.71% for buy and hold; Sharpe 0.49 against 0.72; final multiple 1.79 against 4.95." srcset="https://substackcdn.com/image/fetch/$s_!TkgZ!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27b52f51-7baf-418f-8ba0-5f0db8a6310b_1280x906.png 424w, https://substackcdn.com/image/fetch/$s_!TkgZ!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27b52f51-7baf-418f-8ba0-5f0db8a6310b_1280x906.png 848w, https://substackcdn.com/image/fetch/$s_!TkgZ!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27b52f51-7baf-418f-8ba0-5f0db8a6310b_1280x906.png 1272w, https://substackcdn.com/image/fetch/$s_!TkgZ!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27b52f51-7baf-418f-8ba0-5f0db8a6310b_1280x906.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p>Buy and hold turns one unit into 4.95. Connors turns it into 1.79. Over 13.4 years the strategy that wins 73% of its trades finishes at 36% of the wealth of doing nothing at all &#8212; and loses on Sharpe too, 0.49 against 0.72.</p><p>Look at the second row. With idle cash earning zero instead of the T-bill rate, the account makes 2.91% instead of 4.47%. More than a third of the return (35%) is the money market, not the strategy. That is what "invested a tenth of the time" means in practice, and it is invisible in every per-trade statistic ever posted about this system.</p><blockquote><p>A 73% win rate and a t-statistic of 3.04, and it still finishes at 36% of the wealth of doing nothing.</p></blockquote><p>What it does buy is calm. The worst account drawdown is &#8722;13.2% against the index's &#8722;32.2%, at 5.8% volatility against 16.1%. In the three worst stretches of the period it lost a fraction of what the index lost:</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!GzgG!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F57287fd9-b485-4d88-a879-f4c837899206_1280x680.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!GzgG!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F57287fd9-b485-4d88-a879-f4c837899206_1280x680.png 424w, https://substackcdn.com/image/fetch/$s_!GzgG!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F57287fd9-b485-4d88-a879-f4c837899206_1280x680.png 848w, https://substackcdn.com/image/fetch/$s_!GzgG!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F57287fd9-b485-4d88-a879-f4c837899206_1280x680.png 1272w, https://substackcdn.com/image/fetch/$s_!GzgG!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F57287fd9-b485-4d88-a879-f4c837899206_1280x680.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!GzgG!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F57287fd9-b485-4d88-a879-f4c837899206_1280x680.png" width="1280" height="680" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/57287fd9-b485-4d88-a879-f4c837899206_1280x680.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:680,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:29366,&quot;alt&quot;:&quot;Table: returns in three crashes. COVID: published rules &#8722;4.21%, slower exit &#8722;22.46%, index &#8722;17.68%.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: returns in three crashes. COVID: published rules &#8722;4.21%, slower exit &#8722;22.46%, index &#8722;17.68%." title="Table: returns in three crashes. COVID: published rules &#8722;4.21%, slower exit &#8722;22.46%, index &#8722;17.68%." srcset="https://substackcdn.com/image/fetch/$s_!GzgG!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F57287fd9-b485-4d88-a879-f4c837899206_1280x680.png 424w, https://substackcdn.com/image/fetch/$s_!GzgG!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F57287fd9-b485-4d88-a879-f4c837899206_1280x680.png 848w, https://substackcdn.com/image/fetch/$s_!GzgG!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F57287fd9-b485-4d88-a879-f4c837899206_1280x680.png 1272w, https://substackcdn.com/image/fetch/$s_!GzgG!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F57287fd9-b485-4d88-a879-f4c837899206_1280x680.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p><strong>04 / THREE FIXES</strong></p><h2>Two that fail, one that works</h2><p>A strategy that is right most of the time but under-deployed has an obvious remedy: deploy more. There are three ways to do it and only one of them survives contact with a borrowing cost.</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!cdvs!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0cfcc1b3-8863-42e8-89b2-23ce058d9821_1280x954.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!cdvs!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0cfcc1b3-8863-42e8-89b2-23ce058d9821_1280x954.png 424w, https://substackcdn.com/image/fetch/$s_!cdvs!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0cfcc1b3-8863-42e8-89b2-23ce058d9821_1280x954.png 848w, https://substackcdn.com/image/fetch/$s_!cdvs!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0cfcc1b3-8863-42e8-89b2-23ce058d9821_1280x954.png 1272w, https://substackcdn.com/image/fetch/$s_!cdvs!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0cfcc1b3-8863-42e8-89b2-23ce058d9821_1280x954.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!cdvs!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0cfcc1b3-8863-42e8-89b2-23ce058d9821_1280x954.png" width="1280" height="954" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/0cfcc1b3-8863-42e8-89b2-23ce058d9821_1280x954.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:954,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:42864,&quot;alt&quot;:&quot;Table: the published rules at 1&#215;, 2&#215;, 2.5&#215; and 3&#215; leverage. Sharpe falls from 0.49 to 0.45; at 3&#215; the account makes 8.29% a year against the index's 12.71%.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: the published rules at 1&#215;, 2&#215;, 2.5&#215; and 3&#215; leverage. Sharpe falls from 0.49 to 0.45; at 3&#215; the account makes 8.29% a year against the index's 12.71%." title="Table: the published rules at 1&#215;, 2&#215;, 2.5&#215; and 3&#215; leverage. Sharpe falls from 0.49 to 0.45; at 3&#215; the account makes 8.29% a year against the index's 12.71%." srcset="https://substackcdn.com/image/fetch/$s_!cdvs!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0cfcc1b3-8863-42e8-89b2-23ce058d9821_1280x954.png 424w, https://substackcdn.com/image/fetch/$s_!cdvs!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0cfcc1b3-8863-42e8-89b2-23ce058d9821_1280x954.png 848w, https://substackcdn.com/image/fetch/$s_!cdvs!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0cfcc1b3-8863-42e8-89b2-23ce058d9821_1280x954.png 1272w, https://substackcdn.com/image/fetch/$s_!cdvs!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0cfcc1b3-8863-42e8-89b2-23ce058d9821_1280x954.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p><strong>Fix 1 fails.</strong> Every step of leverage lowers the Sharpe ratio: 0.49 at 1&#215;, 0.46 at 2&#215;, 0.45 at 3&#215;. Even at 3&#215; the account makes 8.29% a year, short of the index's 12.71%, with a &#8722;43.5% drawdown. You are buying return with money borrowed at 5.13% and the edge is not wide enough to pay for it.</p><p><strong>Fix 2, changing the parameters, fails too.</strong> Widening the entry to RSI(2) &lt; 15 and slowing the exit to close &gt; SMA(10) trades more and holds longer, invested 20% of the time. On NYSE sessions it lowers the Sharpe ratio to 0.40 and deepens the worst drawdown to &#8722;29.3%; in the COVID crash it lost &#8722;22.5%. We have withdrawn it.</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!Z4UP!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1bee5107-36ca-4c53-b9ba-3d74f96890f4_1280x1182.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!Z4UP!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1bee5107-36ca-4c53-b9ba-3d74f96890f4_1280x1182.png 424w, https://substackcdn.com/image/fetch/$s_!Z4UP!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1bee5107-36ca-4c53-b9ba-3d74f96890f4_1280x1182.png 848w, https://substackcdn.com/image/fetch/$s_!Z4UP!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1bee5107-36ca-4c53-b9ba-3d74f96890f4_1280x1182.png 1272w, https://substackcdn.com/image/fetch/$s_!Z4UP!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1bee5107-36ca-4c53-b9ba-3d74f96890f4_1280x1182.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!Z4UP!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1bee5107-36ca-4c53-b9ba-3d74f96890f4_1280x1182.png" width="1280" height="1182" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/1bee5107-36ca-4c53-b9ba-3d74f96890f4_1280x1182.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1182,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:50147,&quot;alt&quot;:&quot;Table: holding the index plus 1&#215; extra on signal makes 14.95% a year at Sharpe 0.74, against 12.71% at 0.72 for the index alone.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: holding the index plus 1&#215; extra on signal makes 14.95% a year at Sharpe 0.74, against 12.71% at 0.72 for the index alone." title="Table: holding the index plus 1&#215; extra on signal makes 14.95% a year at Sharpe 0.74, against 12.71% at 0.72 for the index alone." srcset="https://substackcdn.com/image/fetch/$s_!Z4UP!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1bee5107-36ca-4c53-b9ba-3d74f96890f4_1280x1182.png 424w, https://substackcdn.com/image/fetch/$s_!Z4UP!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1bee5107-36ca-4c53-b9ba-3d74f96890f4_1280x1182.png 848w, https://substackcdn.com/image/fetch/$s_!Z4UP!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1bee5107-36ca-4c53-b9ba-3d74f96890f4_1280x1182.png 1272w, https://substackcdn.com/image/fetch/$s_!Z4UP!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1bee5107-36ca-4c53-b9ba-3d74f96890f4_1280x1182.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p><strong>Fix 3 works, and we want to be careful about how loudly we say so.</strong> The overlay beats buy and hold on return at every setting, and it is the only configuration in this piece that also beats it on Sharpe: 0.74 against 0.72 at +1&#215;.</p><p>But read the size of that edge. 2 hundredths of Sharpe is not a discovery; it is a rounding error away from "leverage priced fairly". The +1&#215; overlay adds about 2.2 points of annual return in exchange for 2.9 points of volatility and 3.5 points of drawdown. Most of what you are being paid is compensation for risk you chose to take, and only a sliver is the signal. If someone sells you this as alpha, they are selling you margin.</p><p>Since January 2023 the +1&#215; overlay returned 27.27% a year at a Sharpe of 1.18, against the index's 21.08% at 1.04. Over the recent stretch the overlay wins on both counts, by a margin this short window cannot confirm.</p><p><strong>05 / HOW TO RUN IT</strong></p><h2>Six steps, ten minutes a day, no screen time</h2><p>If you have read the section above and still want to run it, here is the whole procedure. It needs a daily close, three indicators and one order. Nothing here requires watching the market.</p><h3>1. Pick the instrument and the sizing</h3><p>A liquid broad-index ETF &#8212; SPY, VOO or IVV for the S&amp;P 500. Decide up front whether you are running the standalone version (cash when flat) or the overlay (index always held, extra exposure on signal). They are different products with different risks; do not switch between them mid-drawdown.</p><h3>2. After the close, compute three numbers</h3><p>RSI(2), SMA(5) and SMA(200) on daily closes. Any charting package gives you all three. The two-period RSI is the only unusual setting &#8212; most defaults are 14.</p><h3>3. Apply the entry test</h3><p>Flat, and close &gt; SMA(200), and RSI(2) below 10. If all three are true, you buy.</p><h3>4. Place a market-on-open order for tomorrow</h3><p>This is the step that makes the strategy compatible with a job. Our testing shows the next-open fill gives up about 14% of the average trade against Connors' close fill, and the edge stays significant. Submit it the evening before and go to bed.</p><h3>5. Check the exit the same way, every session</h3><p>In a position and close &gt; SMA(5), you sell at the next open. Median holding period is 5 days. There is no stop-loss in the published rules, which is the single largest risk in the system: the worst trade in the record lost 4.23%, entered on 21 February 2020.</p><h3>6. Automate it, or write down what you will do in the dead patch</h3><p>The whole thing is a handful of lines against the IBKR API and it is the most automatable strategy this lab has tested. If you are running it by hand, write down in advance what you will do during three flat years, because 2017&#8211;2019 will happen again and discretion is how systems die.</p><p><strong>RETAIL GATE</strong></p><h2>12 out of 12 &#8212; the first perfect score</h2><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!0uFB!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68ca9d15-1457-4821-b559-a04e9e0256e0_1888x540.png 424w, https://substackcdn.com/image/fetch/$s_!0uFB!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68ca9d15-1457-4821-b559-a04e9e0256e0_1888x540.png 848w, https://substackcdn.com/image/fetch/$s_!0uFB!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68ca9d15-1457-4821-b559-a04e9e0256e0_1888x540.png 1272w, https://substackcdn.com/image/fetch/$s_!0uFB!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68ca9d15-1457-4821-b559-a04e9e0256e0_1888x540.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!0uFB!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68ca9d15-1457-4821-b559-a04e9e0256e0_1888x540.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/68ca9d15-1457-4821-b559-a04e9e0256e0_1888x540.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Retail Gate scorecard&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Retail Gate scorecard" title="Retail Gate scorecard" srcset="https://substackcdn.com/image/fetch/$s_!0uFB!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68ca9d15-1457-4821-b559-a04e9e0256e0_1888x540.png 424w, https://substackcdn.com/image/fetch/$s_!0uFB!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68ca9d15-1457-4821-b559-a04e9e0256e0_1888x540.png 848w, https://substackcdn.com/image/fetch/$s_!0uFB!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68ca9d15-1457-4821-b559-a04e9e0256e0_1888x540.png 1272w, https://substackcdn.com/image/fetch/$s_!0uFB!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F68ca9d15-1457-4821-b559-a04e9e0256e0_1888x540.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div><p>This is the highest Retail Gate score we have recorded, and it deserves stating plainly: the barrier to running Connors RSI(2) is not access, cost, capital or complexity. It is that the thing you would be running does not beat the index unless you lever it, and levering it is most of where the extra return comes from.</p><p><strong>06 / THE TRANSFERABLE PART</strong></p><h2>Ask what the account did, not what the trades did</h2><p>The gap between "profit factor 2.13, t-statistic 3.04" and "36% of the wealth of doing nothing" is not a contradiction. Both are true. They answer different questions, and only one of them is the question you have.</p><p>Any strategy that sits in cash has this problem, and the less time it spends invested the worse it gets. A swing system that is in the market a tenth of the time can have a beautiful trade distribution and still leave you poorer than a savings account plus an index fund, because ninety per cent of your capital was doing nothing while the market compounded without you. Win rate, profit factor, average trade and t-statistic are all silent on this. They are computed over trades, and the trades are not your life.</p><p>Three questions turn a per-trade claim into an account claim. <strong>What percentage of the time is it invested?</strong> Below about 30% and you should assume the headline is misleading until proven otherwise. <strong>What is the idle capital earning?</strong> In this case more than a third of the total return, which means the same strategy would have looked substantially worse in the zero-rate years and the backtest quietly took credit for the Federal Reserve. <strong>And what did buy and hold do over the identical window?</strong> Not the strategy's own equity curve in isolation &#8212; the alternative you actually had.</p><p>None of this makes Connors RSI(2) a bad system. It is a genuine, replicable, statistically significant edge, it is the most retail-runnable thing we have tested, and it protects capital in crashes in a way holding the index does not. It is simply much smaller than it looks, and where you deploy it matters more than whether you have it.</p><h3>Method</h3><p>Data: Dukascopy 1-minute bid, resampled to regular-hours daily bars on NYSE trading sessions only. US 500, 3,365 sessions, 2013-04-16 to 2026-08-31; US Tech 100, 3,435 sessions, used as the second-instrument check. Annual figures use calendar years. Indicators are Pine-compatible: RSI on an SMA-seeded Wilder average, SMAs on closes.</p><p>Per-trade tests: entry and exit both at the signal-day close (Connors' convention) or both at the following session's open, 3 basis points charged per round trip. Account tests: open-to-open index returns while held, the daily 4-week T-bill on idle balances, cost charged on each side of a position change, leverage financed at 5.13% &#8212; the Interactive Brokers retail tier for balances under $100,000. Positions are decided at the close and filled at the next open throughout, so no result uses information it could not have had.</p><p>An earlier note in our batch-1 write-up described this strategy as returning "roughly 3&#215; per unit of exposure at a fifth of the drawdown". On NYSE sessions the per-contract drawdown in batch 1 is about a third of buy-and-hold's (&#8722;$19,710 against &#8722;$60,978), not a fifth, and as a headline the per-trade framing is misleading &#8212; it is the framing this piece exists to correct. The account-level comparison above supersedes it.</p><h3>Sources</h3><p>Larry Connors and Cesar Alvarez, <em>Short Term Trading Strategies That Work</em> (2008), for the original rules &#183; Batch 1 verification, this lab, 1 September 2026 &#183; Interactive Brokers published margin rates</p><p>Backtested results are hypothetical and do not represent returns any investor achieved. This is research, not investment advice.</p>]]></content:encoded></item><item><title><![CDATA[The Century That Ended in 1990]]></title><description><![CDATA[A 100-year industry trend strategy replicates at 18.2% a year. 63% of the growth came before 1980.]]></description><link>https://www.pastperformancelab.com/p/industry-trend-following-100-year-backtest</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/industry-trend-following-100-year-backtest</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Wed, 02 Sep 2026 14:00:00 GMT</pubDate><enclosure url="https://substack-post-media.s3.amazonaws.com/public/images/1858445c-b3f7-4679-a2c2-72daa251b616_1888x922.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Strategy Verification &#183; Issue 04 &#183; 2 September 2026 &#183; a century of daily data</em></p><p><em>Updated 27 Sep 2026: annual figures now use calendar years (the daily data carry Saturday sessions before 1952) and a daily T-bill series. On the paper's own convention the replication still matches to a tenth of a point; the verdict is unchanged.</em></p><p><em>Carlo Zarattini and Gary Antonacci published a trend-following strategy that returned 18.2% a year for a hundred years. We reproduced it to within a tenth of a point &#8212; and then found that everything you could actually buy it with has lost to the index since 2006.</em></p><p><strong>Replicates &#183; Edge is pre-1990 &#183; Fails on tradeable instruments</strong><br><em>18.27% claimed 18.2% (19.14% on calendar years) &nbsp;&#183;&nbsp; investable version 5.85% vs market 11.37%</em></p><p><strong>01 / THE CLAIM</strong></p><h2>A hundred years, 18.2% a year, a third of the market's drawdown</h2><p><a href="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4857230">A Century of Profitable Industry Trends</a> is a serious paper by serious people. Gary Antonacci wrote the book on dual momentum; Carlo Zarattini runs <a href="https://concretumgroup.com/a-century-of-profitable-industry-trends/">Concretum</a> and publishes more replicable research than most academics. The paper is fully specified &#8212; every band, every parameter, every sizing rule is in the text &#8212; which is precisely why it was worth testing.</p><p>The rules are compact. Build a price index for each of Ken French's 48 industry portfolios. Around each one draw two channels: a Donchian channel on closing prices, and a Keltner channel adapted to closes, <code>EMA(P,n) &#177; 1.4&#183;k&#183;mean(|&#916;P|,n)</code>. Go long when the price closes at or above the <em>lower</em> of the two upper bands. Exit on a trailing stop set to the <em>higher</em> of the two lower bands, ratcheted so it is never revised down. Size each position at <code>(1.5%/N) &#247; &#963;</code> on 14-day volatility, cap gross exposure at 200%, rebalance daily, park cash in one-month T-bills.</p><p>Long only. No shorting, no options, no leverage beyond 2&#215;. The claimed result is an 18.2% internal rate of return at 12.6% volatility with a 33% maximum drawdown, against a market that lost 84% of its value at the bottom of 1932.</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!AnpO!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F34a04667-3ff1-4008-bc81-cc48f366485a_1280x1106.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!AnpO!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F34a04667-3ff1-4008-bc81-cc48f366485a_1280x1106.png 424w, https://substackcdn.com/image/fetch/$s_!AnpO!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F34a04667-3ff1-4008-bc81-cc48f366485a_1280x1106.png 848w, https://substackcdn.com/image/fetch/$s_!AnpO!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F34a04667-3ff1-4008-bc81-cc48f366485a_1280x1106.png 1272w, https://substackcdn.com/image/fetch/$s_!AnpO!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F34a04667-3ff1-4008-bc81-cc48f366485a_1280x1106.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!AnpO!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F34a04667-3ff1-4008-bc81-cc48f366485a_1280x1106.png" width="1280" height="1106" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/34a04667-3ff1-4008-bc81-cc48f366485a_1280x1106.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1106,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:43983,&quot;alt&quot;:&quot;Table: the paper reports 18.2% a year; our replication gives 18.27% on the paper's convention and 19.14% on calendar years, against 10.08% for the market.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: the paper reports 18.2% a year; our replication gives 18.27% on the paper's convention and 19.14% on calendar years, against 10.08% for the market." title="Table: the paper reports 18.2% a year; our replication gives 18.27% on the paper's convention and 19.14% on calendar years, against 10.08% for the market." srcset="https://substackcdn.com/image/fetch/$s_!AnpO!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F34a04667-3ff1-4008-bc81-cc48f366485a_1280x1106.png 424w, https://substackcdn.com/image/fetch/$s_!AnpO!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F34a04667-3ff1-4008-bc81-cc48f366485a_1280x1106.png 848w, https://substackcdn.com/image/fetch/$s_!AnpO!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F34a04667-3ff1-4008-bc81-cc48f366485a_1280x1106.png 1272w, https://substackcdn.com/image/fetch/$s_!AnpO!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F34a04667-3ff1-4008-bc81-cc48f366485a_1280x1106.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p>That is a clean replication. The paper says what it did, and doing what it says produces what it reports. Most of what circulates as a "backtested strategy" does not survive this step. This one does, and that is the reason the rest of this piece is worth reading &#8212; everything below is built on numbers the authors would recognise as their own.</p><p><strong>02 / THE FIRST THING THE HEADLINE HIDES</strong></p><h2>Sixty-three per cent of the century was made before 1980</h2><p>A hundred-year average is a single number laid over eleven very different decades. Split it, and the strategy's excess return over the market has a shape nobody would advertise.</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!9T4e!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa8da304c-6c4b-48ac-b656-6a0b088b262c_1280x1016.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!9T4e!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa8da304c-6c4b-48ac-b656-6a0b088b262c_1280x1016.png 424w, https://substackcdn.com/image/fetch/$s_!9T4e!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa8da304c-6c4b-48ac-b656-6a0b088b262c_1280x1016.png 848w, https://substackcdn.com/image/fetch/$s_!9T4e!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa8da304c-6c4b-48ac-b656-6a0b088b262c_1280x1016.png 1272w, https://substackcdn.com/image/fetch/$s_!9T4e!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa8da304c-6c4b-48ac-b656-6a0b088b262c_1280x1016.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!9T4e!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa8da304c-6c4b-48ac-b656-6a0b088b262c_1280x1016.png" width="1280" height="1016" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/a8da304c-6c4b-48ac-b656-6a0b088b262c_1280x1016.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1016,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:28708,&quot;alt&quot;:&quot;Bar chart: the strategy's excess annual return over the US market by decade, positive every decade from the 1920s to the 2000s and negative in the 2010s and 2020s.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Bar chart: the strategy's excess annual return over the US market by decade, positive every decade from the 1920s to the 2000s and negative in the 2010s and 2020s." title="Bar chart: the strategy's excess annual return over the US market by decade, positive every decade from the 1920s to the 2000s and negative in the 2010s and 2020s." srcset="https://substackcdn.com/image/fetch/$s_!9T4e!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa8da304c-6c4b-48ac-b656-6a0b088b262c_1280x1016.png 424w, https://substackcdn.com/image/fetch/$s_!9T4e!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa8da304c-6c4b-48ac-b656-6a0b088b262c_1280x1016.png 848w, https://substackcdn.com/image/fetch/$s_!9T4e!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa8da304c-6c4b-48ac-b656-6a0b088b262c_1280x1016.png 1272w, https://substackcdn.com/image/fetch/$s_!9T4e!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa8da304c-6c4b-48ac-b656-6a0b088b262c_1280x1016.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p>Excess return is the strategy's compound annual return minus the US total-market return over the same days, annualised by calendar years. Partial decades at each end (1926&#8211;29, 2020&#8211;Mar 2024) are computed on the days available.</p><p>The strategy beat the market in every decade from the 1920s to the 1980s, by more than eleven points a year in all of them but the 1930s (+7.0). Then the 1990s came in flat. The 2000s look like a return to form at +9.2, but read what happened: the market went nowhere that decade, losing 0.39% a year and drawing down 54.6%. The strategy made 8.76% by sitting in cash through two crashes. That is defence, not edge.</p><p>Then the 2010s: &#8722;3.98. The 2020s so far: &#8722;3.87. Sixty-three per cent of the century's total compound growth was banked before 1980, in industry portfolios that were not investable, at a turnover nobody could have paid for, in an era when the average holding cost of a US equity position was an order of magnitude higher than today.</p><blockquote><p>Every decade from the 1920s to the 1980s: ahead of the market. Every decade since 2010: behind it.</p></blockquote><p><strong>03 / THE SECOND THING</strong></p><h2>You cannot buy a Ken French industry portfolio</h2><p>The 48 industry portfolios are academic constructs &#8212; value-weighted baskets of every CRSP-listed firm in a SIC bucket, rebalanced each June, with no fund behind them. To trade this you need the paper's second test: SPDR sector and industry ETFs. That version is the one a retail investor could actually run, and it is the one the abstract does not lead with.</p><p>We rebuilt it with the same engine on <code>XLB XLE XLF XLI XLK XLP XLU XLV XLY XLRE XLC</code> plus the industry SPDRs <code>KBE KCE KIE KRE XAR XBI XES XHB XHE XHS XITK XME XNTK XOP XPH XRT XSD XSW XTH XTL XTN XWEB</code> &#8212; every one of them available in any brokerage account, commission-free at most brokers. Twenty and a half years, January 2006 to June 2026.</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!7OI-!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2eb10b31-dd1f-497a-af66-422f450189d1_1280x758.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!7OI-!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2eb10b31-dd1f-497a-af66-422f450189d1_1280x758.png 424w, https://substackcdn.com/image/fetch/$s_!7OI-!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2eb10b31-dd1f-497a-af66-422f450189d1_1280x758.png 848w, https://substackcdn.com/image/fetch/$s_!7OI-!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2eb10b31-dd1f-497a-af66-422f450189d1_1280x758.png 1272w, https://substackcdn.com/image/fetch/$s_!7OI-!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2eb10b31-dd1f-497a-af66-422f450189d1_1280x758.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!7OI-!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2eb10b31-dd1f-497a-af66-422f450189d1_1280x758.png" width="1280" height="758" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/2eb10b31-dd1f-497a-af66-422f450189d1_1280x758.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:758,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:39709,&quot;alt&quot;:&quot;Table: the ETF version makes 7.97% a year on the paper's assumptions against 11.37% for the market; real margin and costs lower it further.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: the ETF version makes 7.97% a year on the paper's assumptions against 11.37% for the market; real margin and costs lower it further." title="Table: the ETF version makes 7.97% a year on the paper's assumptions against 11.37% for the market; real margin and costs lower it further." srcset="https://substackcdn.com/image/fetch/$s_!7OI-!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2eb10b31-dd1f-497a-af66-422f450189d1_1280x758.png 424w, https://substackcdn.com/image/fetch/$s_!7OI-!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2eb10b31-dd1f-497a-af66-422f450189d1_1280x758.png 848w, https://substackcdn.com/image/fetch/$s_!7OI-!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2eb10b31-dd1f-497a-af66-422f450189d1_1280x758.png 1272w, https://substackcdn.com/image/fetch/$s_!7OI-!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2eb10b31-dd1f-497a-af66-422f450189d1_1280x758.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p>On the authors' own generous assumptions &#8212; free trading, institutional borrowing &#8212; the investable version returns 7.97% against the market's 11.37%, at a Sharpe of 0.51 against 0.57. It loses on return and it loses on risk-adjusted return. Charge the margin rate an actual retail account pays and five basis points to trade, and it makes 5.85%: barely half the index, for 2,270% annual turnover and a 28.2% win rate across 2,934 trades.</p><p>The one thing it delivers is the drawdown promise. &#8722;23.4% against the market's &#8722;54.6%. Hold that thought; we come back to it.</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!QkMf!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F79451b03-a042-4dd2-9d3a-4406cee53981_1280x678.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!QkMf!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F79451b03-a042-4dd2-9d3a-4406cee53981_1280x678.png 424w, https://substackcdn.com/image/fetch/$s_!QkMf!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F79451b03-a042-4dd2-9d3a-4406cee53981_1280x678.png 848w, https://substackcdn.com/image/fetch/$s_!QkMf!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F79451b03-a042-4dd2-9d3a-4406cee53981_1280x678.png 1272w, https://substackcdn.com/image/fetch/$s_!QkMf!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F79451b03-a042-4dd2-9d3a-4406cee53981_1280x678.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!QkMf!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F79451b03-a042-4dd2-9d3a-4406cee53981_1280x678.png" width="1280" height="678" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/79451b03-a042-4dd2-9d3a-4406cee53981_1280x678.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:678,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:28711,&quot;alt&quot;:&quot;Table: since April 2024 the ETF version makes 8.95% a year and the 48-industry version 5.51%, against 18.96% for the market.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: since April 2024 the ETF version makes 8.95% a year and the 48-industry version 5.51%, against 18.96% for the market." title="Table: since April 2024 the ETF version makes 8.95% a year and the 48-industry version 5.51%, against 18.96% for the market." srcset="https://substackcdn.com/image/fetch/$s_!QkMf!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F79451b03-a042-4dd2-9d3a-4406cee53981_1280x678.png 424w, https://substackcdn.com/image/fetch/$s_!QkMf!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F79451b03-a042-4dd2-9d3a-4406cee53981_1280x678.png 848w, https://substackcdn.com/image/fetch/$s_!QkMf!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F79451b03-a042-4dd2-9d3a-4406cee53981_1280x678.png 1272w, https://substackcdn.com/image/fetch/$s_!QkMf!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F79451b03-a042-4dd2-9d3a-4406cee53981_1280x678.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p><strong>04 / FIVE GATES</strong></p><h2>We tried to break our own result, then tried to rescue theirs</h2><p>A negative finding is only worth publishing if you have attacked it as hard as you would attack a positive one. Five tests, in the order we ran them. The first two ask whether our engine is trustworthy. The last three ask whether the strategy can be saved.</p><h3>01 &#183; Does the engine peek at the future?</h3><p>Feed it twenty random walks with the same drift and the same volatility as the real industry portfolios. A clean engine can only earn the drift. An engine with lookahead earns more.</p><p><strong>CLEAN.</strong> Strategy returns 8.79% on random walks against a 12.72% buy-and-hold drift &#8212; it <em>underperforms</em> by 3.94 points, exactly as a system with no edge and periodic cash holdings should. Standard deviation across seeds 0.29.</p><h3>02 &#183; Are the published parameters a lucky cell?</h3><p>Eight settings around the published 20-day entry / 40-day exit / k = 2, tested on the investable ETF universe.</p><p><strong>NOT A KNIFE-EDGE &#8212; AND THAT MAKES IT WORSE.</strong> All eight land between 4.71% and 6.72% after realistic costs, against 11.39% for buy and hold. Robust, and robustly behind the index. Worth saying plainly: the published parameters are not even the best cell we found, so there is no sign the authors tuned to the answer.</p><h3>03 &#183; Can the turnover be cut to something a person could run?</h3><p>2,270% a year is the retail killer &#8212; that is every position turned over twenty-three times annually, in a taxable account, on daily closes. So: keep the daily stop, because you must always be able to get out, but only add positions and resize weekly or monthly.</p><p><strong>NO.</strong> Weekly rebalancing cuts turnover from 22.6&#215; to 14.5&#215; and the return from 5.92% to 5.04%. Monthly cuts turnover to 7.4&#215; and the return to <strong>2.50%</strong>. The return falls faster than the cost it saves. There is no low-turnover version of this strategy.</p><h3>04 &#183; Is the trend signal doing any work at all?</h3><p>Gate 03 implies something specific: if slowing the rebalance destroys the return, maybe the return lives in the rebalance and not in the signal. So strip the signal out entirely &#8212; same volatility-target sizing, same 200% cap, same daily rebalance, but always long everything.</p><p><strong>OVER THE CENTURY, YES. ON TRADEABLE INSTRUMENTS, NO.</strong> On the paper's own conventions, across 48 industries 1926&#8211;2024 the signal earns its keep: 18.31% at Sharpe 1.15 and &#8722;33.6% drawdown, against 14.41% at Sharpe 0.67 and &#8722;78.9% with the signal off. But on the ETFs since 2006, turning the signal <em>off</em> returns 11.75% at Sharpe 0.58 &#8212; better than the 8.03% at 0.51 you get with it on.</p><h3>05 &#183; Would random entries have done as well?</h3><p>The control that separates a signal from a sizing scheme: enter and exit at random, matched to the real strategy's 65% time-in-market, run through the identical volatility-targeting machinery.</p><p><strong>ONLY IF TRADING WERE FREE.</strong> Random entries reach Sharpe 0.64&#8211;0.65 at zero cost &#8212; comparable to the real signal. But they turn over 163&#8211;207&#215; a year, and at 5bp the random arm collapses to 0.00 and &#8722;0.22. What the trend rules genuinely provide is not the edge; it is doing the volatility targeting at a turnover low enough to survive friction.</p><p><strong>05 / WHAT SURVIVES</strong></p><h2>A drawdown machine, priced as an alpha machine</h2><p>There is something real here, and it is not the 18.2%.</p><p>Across the investable universe the strategy cut the worst drawdown from &#8722;54.6% to &#8722;23.4% &#8212; less than half &#8212; and did it at 13.7% volatility against the market's 19.6%. In the 2000s that protection was worth +9.2 points a year, because avoiding two crashes was the whole game. In the 2010s and 2020s it cost about four points a year, because there was nothing to avoid and plenty to miss.</p><p>So the honest description is: this is a defensive equity allocation with an unusually good crisis record and a persistent drag in trending markets. Whether that is worth owning depends entirely on what you think the next decade looks like &#8212; which is a forecast, not a backtest, and the paper's abstract does not present it as one.</p><p>The independent critique reaches a compatible conclusion from a different direction. <a href="https://arxiv.org/abs/2412.14361">Refining and Robust Backtesting of A Century of Profitable Industry Trends</a> attempted a walk-forward validation and could not confirm the result, concluding the original was likely overfit. We did not test for overfitting &#8212; we tested for tradeability &#8212; and arrived at the same place by another road.</p><p><strong>RETAIL GATE</strong></p><h2>Could you run it, if it worked?</h2><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!1wga!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffaaab914-0ff5-4a63-bb4e-9064b6bec0c8_1888x738.png 424w, https://substackcdn.com/image/fetch/$s_!1wga!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffaaab914-0ff5-4a63-bb4e-9064b6bec0c8_1888x738.png 848w, https://substackcdn.com/image/fetch/$s_!1wga!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffaaab914-0ff5-4a63-bb4e-9064b6bec0c8_1888x738.png 1272w, https://substackcdn.com/image/fetch/$s_!1wga!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffaaab914-0ff5-4a63-bb4e-9064b6bec0c8_1888x738.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!1wga!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffaaab914-0ff5-4a63-bb4e-9064b6bec0c8_1888x738.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/faaab914-0ff5-4a63-bb4e-9064b6bec0c8_1888x738.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Retail Gate scorecard&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Retail Gate scorecard" title="Retail Gate scorecard" srcset="https://substackcdn.com/image/fetch/$s_!1wga!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffaaab914-0ff5-4a63-bb4e-9064b6bec0c8_1888x738.png 424w, https://substackcdn.com/image/fetch/$s_!1wga!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffaaab914-0ff5-4a63-bb4e-9064b6bec0c8_1888x738.png 848w, https://substackcdn.com/image/fetch/$s_!1wga!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffaaab914-0ff5-4a63-bb4e-9064b6bec0c8_1888x738.png 1272w, https://substackcdn.com/image/fetch/$s_!1wga!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffaaab914-0ff5-4a63-bb4e-9064b6bec0c8_1888x738.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div><p><strong>7 out of 12.</strong> The barriers are cadence and complexity, not money or access &#8212; which is the unusual case where automation genuinely solves the retail problem. It would be a good candidate for a hands-off implementation, if the returns were there. They are not.</p><p><strong>06 / THE TRANSFERABLE PART</strong></p><h2>What to check before you trust a long backtest</h2><p>Three questions, in this order, and they generalise well beyond this paper.</p><p><strong>Could you have traded the instruments?</strong> A century of industry portfolios is a century of academic constructs. Sector ETFs are twenty years old, and the SPDR industry funds mostly younger than that. Any result whose good years pre-date the vehicles is a result about a market that could not be accessed.</p><p><strong>Where is the return concentrated in time?</strong> Not "is the average good" but "which decades paid for the average". If more than half the compound growth lands before the era you would actually be trading in, the headline is a historical claim, not a forward one.</p><p><strong>What does the strategy cost to run, at your rates?</strong> The paper borrows at the one-month T-bill rate. A retail account at Interactive Brokers under $100,000 pays benchmark plus 1.5% &#8212; 5.13% at the time of writing. Over a century that gap costs almost a point of annual return; in the modern era, where the strategy's total excess return is negative anyway, it is the difference between a marginal idea and a clearly bad one.</p><p>None of this is a criticism of the authors' honesty. Their paper specifies its rules completely enough that a stranger could reproduce it in an afternoon, which is more than can be said for almost anything posted on a chart. That is the standard. The finding is simply that the strategy those rules describe stopped working around the time the instruments to trade it were invented.</p><h3>Method</h3><p>Data: Ken French Data Library, 48 Industry Portfolios daily value-weighted returns and F-F Research Data Factors daily (RF, Mkt-RF), July 1926 &#8211; June 2026; the strategy runs to March 2024 (25,710 daily rows, which include Saturday sessions until May 1952, so annual figures use calendar years). Cash earns a daily T-bill series. The five gates were run on the paper's own conventions (one-month T-bill, 252 rows a year) and are unchanged. ETF prices: adjusted daily closes for 33 SPDR sector and industry funds, of which 25 have fifteen or more years of history; funds enter the universe on their listing date and take no risk budget before it.</p><p>Engine: bands computed on closing prices only. Entry compares today's close to yesterday's upper band. The trailing stop uses today's lower band and is never revised down. Position weights are set at the close and applied to the following day's returns, so no decision uses information it could not have had. Risk budget is divided by the number of assets available that day, not the nominal universe size.</p><p>Costs: leverage financed at the one-month T-bill rate in the paper's configuration and at 5.13% in the retail configuration. Friction charged in basis points of turnover; the 5bp case corresponds to roughly a half-cent spread on a $50 ETF plus commission.</p><h3>Sources</h3><p>Carlo Zarattini and Gary Antonacci, <a href="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4857230">A Century of Profitable Industry Trends</a>, SSRN 4857230 &#183; <a href="https://arxiv.org/abs/2412.14361">Refining and Robust Backtesting of A Century of Profitable Industry Trends</a>, arXiv:2412.14361 &#183; <a href="https://mba.tuck.dartmouth.edu/pages/faculty/ken.french/data_library.html">Ken French Data Library</a> &#183; <a href="https://concretumgroup.com/a-century-of-profitable-industry-trends/">Concretum Group</a></p><p>Backtested results are hypothetical and do not represent returns any investor achieved. This is research, not investment advice.</p>]]></content:encoded></item><item><title><![CDATA[The Missing Ten Weeks]]></title><description><![CDATA[MrMilkTrading's weekly SPX put credit spread really wins 95% of the time. Its backtest starts just after the 2020 crash.]]></description><link>https://www.pastperformancelab.com/p/spx-put-credit-spread-backtest-2020</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/spx-put-credit-spread-backtest-2020</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Wed, 02 Sep 2026 11:00:00 GMT</pubDate><enclosure url="https://substack-post-media.s3.amazonaws.com/public/images/955622fd-ceb3-495c-8191-2de5a878c064_1888x204.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Verification Batch 02 &#183; SPX weekly put credit spread &#183; 2 September 2026</em></p><p><em><a href="https://x.com/MrMilkTrading/status/2088011906384552045">The Milk Man</a> published a complete SPX strategy &#8212; 95.4% win rate, $4,605 maximum drawdown, every rule stated. We reproduced his win rate to within a tenth of a point. Then we ran the same rule over thirteen years instead of six, and found that three of the four worst weeks in that history sit just outside his start date.</em></p><p><strong>Survives &#183; Risk understated 5&#8211;10&#215;</strong></p><h2>The claim</h2><p><strong>One spread a week, at one level</strong></p><p><a href="https://x.com/MrMilkTrading/status/2088011906384552045">The Milk Man (@MrMilkTrading)</a> posted it in full: <em>"Sell one SPX put credit spread per week at the Multi-Day Saty ATR &#8722;1 level. That's the whole strategy."</em> Reported: 326 trades since May 2020, 95.4% win rate, profit factor 2.48, +$53,328 on a single contract, maximum drawdown $4,605.</p><p>His <a href="https://milkmantrades.com/atr-premium-selling.html">own site</a> fills in the rest, and we used it: 50-point spread width, weekly SPXW expiry, entry on the first trading day of the week around 10:00 ET, short strike rounded to the nearest 5, average credit $298, $2.64 commission, hold to settlement with no stop and no adjustment. Maximum risk per lot, about $4,702.</p><p>The level resolves exactly from the indicator's open source: Multi-Day means the weekly timeframe, and the &#8722;1 level is the previous weekly close minus the weekly 14-period ATR. That is fully reproducible, which is more than can be said for most strategies that circulate with numbers attached.</p><p>It also makes the first check free. A spread held to expiry either settles above the short strike, keeping the whole credit, or below it, losing up to the width. Deciding which happened needs only the index and the strike &#8212; no options data at all.</p><h2>First finding</h2><p><strong>His win rate is honest</strong></p><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!qoDj!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70bb70c9-17a1-45cc-88a9-b5311e85ba7e_1888x204.png 424w, https://substackcdn.com/image/fetch/$s_!qoDj!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70bb70c9-17a1-45cc-88a9-b5311e85ba7e_1888x204.png 848w, https://substackcdn.com/image/fetch/$s_!qoDj!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70bb70c9-17a1-45cc-88a9-b5311e85ba7e_1888x204.png 1272w, https://substackcdn.com/image/fetch/$s_!qoDj!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70bb70c9-17a1-45cc-88a9-b5311e85ba7e_1888x204.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!qoDj!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70bb70c9-17a1-45cc-88a9-b5311e85ba7e_1888x204.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/70bb70c9-17a1-45cc-88a9-b5311e85ba7e_1888x204.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Key figures&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Key figures" title="Key figures" srcset="https://substackcdn.com/image/fetch/$s_!qoDj!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70bb70c9-17a1-45cc-88a9-b5311e85ba7e_1888x204.png 424w, https://substackcdn.com/image/fetch/$s_!qoDj!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70bb70c9-17a1-45cc-88a9-b5311e85ba7e_1888x204.png 848w, https://substackcdn.com/image/fetch/$s_!qoDj!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70bb70c9-17a1-45cc-88a9-b5311e85ba7e_1888x204.png 1272w, https://substackcdn.com/image/fetch/$s_!qoDj!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70bb70c9-17a1-45cc-88a9-b5311e85ba7e_1888x204.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div><p>This deserves to be said before anything else. The number reproduces. The same author's Phase Oscillator strategy also reproduced when we tested it, to within 3.5% on net profit with an identical maximum drawdown. He publishes figures that survive checking, which in this corner of the internet is unusual enough to be worth stating plainly.</p><h2>Second finding</h2><p><strong>A 95% win rate here is arithmetic, not skill</strong></p><p>A put credit spread wins whenever the index fails to fall past the strike. Placed one weekly ATR below the market, that is <em>supposed</em> to happen about ninety-five times in a hundred. The win rate is the design of the instrument, not evidence of an edge in it.</p><p>Decompose his own published figures and the shape becomes clear.</p><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!_L6J!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffdec7cc4-45f7-4660-a3d5-493f7ac9e1ba_1888x206.png 424w, https://substackcdn.com/image/fetch/$s_!_L6J!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffdec7cc4-45f7-4660-a3d5-493f7ac9e1ba_1888x206.png 848w, https://substackcdn.com/image/fetch/$s_!_L6J!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffdec7cc4-45f7-4660-a3d5-493f7ac9e1ba_1888x206.png 1272w, https://substackcdn.com/image/fetch/$s_!_L6J!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffdec7cc4-45f7-4660-a3d5-493f7ac9e1ba_1888x206.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!_L6J!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffdec7cc4-45f7-4660-a3d5-493f7ac9e1ba_1888x206.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/fdec7cc4-45f7-4660-a3d5-493f7ac9e1ba_1888x206.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Key figures&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Key figures" title="Key figures" srcset="https://substackcdn.com/image/fetch/$s_!_L6J!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffdec7cc4-45f7-4660-a3d5-493f7ac9e1ba_1888x206.png 424w, https://substackcdn.com/image/fetch/$s_!_L6J!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffdec7cc4-45f7-4660-a3d5-493f7ac9e1ba_1888x206.png 848w, https://substackcdn.com/image/fetch/$s_!_L6J!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffdec7cc4-45f7-4660-a3d5-493f7ac9e1ba_1888x206.png 1272w, https://substackcdn.com/image/fetch/$s_!_L6J!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffdec7cc4-45f7-4660-a3d5-493f7ac9e1ba_1888x206.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div><p>Everything therefore depends on the losses staying rare <em>and</em> staying apart. His stated worst case is a single maximum loss &#8212; so the claim is, in effect, that two bad weeks never landed close together. In February 2020 three landed inside four weeks.</p><h2>Third finding</h2><p><strong>The start date is doing the work</strong></p><p>Run the identical rule from 2013 rather than May 2020 and the picture changes &#8212; not catastrophically, but materially, and in the place that matters.</p><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!7aPG!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcac612d8-bb88-4b56-a751-02cd49f5cb7d_2000x838.png 424w, https://substackcdn.com/image/fetch/$s_!7aPG!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcac612d8-bb88-4b56-a751-02cd49f5cb7d_2000x838.png 848w, https://substackcdn.com/image/fetch/$s_!7aPG!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcac612d8-bb88-4b56-a751-02cd49f5cb7d_2000x838.png 1272w, https://substackcdn.com/image/fetch/$s_!7aPG!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcac612d8-bb88-4b56-a751-02cd49f5cb7d_2000x838.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!7aPG!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcac612d8-bb88-4b56-a751-02cd49f5cb7d_2000x838.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/cac612d8-bb88-4b56-a751-02cd49f5cb7d_2000x838.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Worst weeks, 2013&#8211;2026Below strikeIn ATR terms&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Worst weeks, 2013&#8211;2026Below strikeIn ATR terms" title="Worst weeks, 2013&#8211;2026Below strikeIn ATR terms" srcset="https://substackcdn.com/image/fetch/$s_!7aPG!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcac612d8-bb88-4b56-a751-02cd49f5cb7d_2000x838.png 424w, https://substackcdn.com/image/fetch/$s_!7aPG!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcac612d8-bb88-4b56-a751-02cd49f5cb7d_2000x838.png 848w, https://substackcdn.com/image/fetch/$s_!7aPG!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcac612d8-bb88-4b56-a751-02cd49f5cb7d_2000x838.png 1272w, https://substackcdn.com/image/fetch/$s_!7aPG!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcac612d8-bb88-4b56-a751-02cd49f5cb7d_2000x838.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div><p><em>Shaded rows fall outside the tested window. The short strike sits at 1&#215; ATR &#8212; a 4.57&#215; ATR week is not a tail the position size contemplates.</em></p><h3>The finding</h3><blockquote><p>Three of the four worst weeks in thirteen years fall in February and March 2020 &#8212; the ten weeks immediately before the backtest begins. A May 2020 start date excludes the single worst cluster for a short-put strategy in modern history, and misses it by six weeks.</p></blockquote><h2>Priced out</h2><p><strong>What it looks like over thirteen years</strong></p><p>To put money on the outcomes we need the credit received, and that is the one thing the index alone cannot tell us. Rather than model option prices and inherit the model's errors, we used <em>his own</em> stated average of $298 a week. Using the author's number is more defensible than any pricing model we could build, and it is generous to him, because that credit was earned in the window he chose. No options data was purchased for any of this.</p><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!O41h!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff0993470-d354-47c4-8ea6-c6d20e051689_2000x628.png 424w, https://substackcdn.com/image/fetch/$s_!O41h!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff0993470-d354-47c4-8ea6-c6d20e051689_2000x628.png 848w, https://substackcdn.com/image/fetch/$s_!O41h!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff0993470-d354-47c4-8ea6-c6d20e051689_2000x628.png 1272w, https://substackcdn.com/image/fetch/$s_!O41h!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff0993470-d354-47c4-8ea6-c6d20e051689_2000x628.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!O41h!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff0993470-d354-47c4-8ea6-c6d20e051689_2000x628.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/f0993470-d354-47c4-8ea6-c6d20e051689_2000x628.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;50-point width, his exact specNetProfit factorMax drawdown&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="50-point width, his exact specNetProfit factorMax drawdown" title="50-point width, his exact specNetProfit factorMax drawdown" srcset="https://substackcdn.com/image/fetch/$s_!O41h!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff0993470-d354-47c4-8ea6-c6d20e051689_2000x628.png 424w, https://substackcdn.com/image/fetch/$s_!O41h!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff0993470-d354-47c4-8ea6-c6d20e051689_2000x628.png 848w, https://substackcdn.com/image/fetch/$s_!O41h!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff0993470-d354-47c4-8ea6-c6d20e051689_2000x628.png 1272w, https://substackcdn.com/image/fetch/$s_!O41h!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff0993470-d354-47c4-8ea6-c6d20e051689_2000x628.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div><p><em>Our reconstruction on his own window comes out better than his own reporting (PF 2.54 against his 2.48), so this is not a lowball. Two credit models bracket the truth: a flat $298 every week overstates premium in calm markets, while scaling credit to prevailing volatility probably understates it. Reality sits between them &#8212; and both land far below his window. Profit factor falls from ~2.5 to between 1.73 and 1.12; maximum drawdown grows from about $6,000 to between $22,837 and $46,136, five to ten times the published figure.</em></p><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!_1pL!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feeeb47db-3577-4204-a507-c34c1255fdbd_2000x1052.png 424w, https://substackcdn.com/image/fetch/$s_!_1pL!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feeeb47db-3577-4204-a507-c34c1255fdbd_2000x1052.png 848w, https://substackcdn.com/image/fetch/$s_!_1pL!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feeeb47db-3577-4204-a507-c34c1255fdbd_2000x1052.png 1272w, https://substackcdn.com/image/fetch/$s_!_1pL!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feeeb47db-3577-4204-a507-c34c1255fdbd_2000x1052.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!_1pL!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feeeb47db-3577-4204-a507-c34c1255fdbd_2000x1052.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/eeeb47db-3577-4204-a507-c34c1255fdbd_2000x1052.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Annual P&amp;L, full history, scaled creditResult&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Annual P&amp;L, full history, scaled creditResult" title="Annual P&amp;L, full history, scaled creditResult" srcset="https://substackcdn.com/image/fetch/$s_!_1pL!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feeeb47db-3577-4204-a507-c34c1255fdbd_2000x1052.png 424w, https://substackcdn.com/image/fetch/$s_!_1pL!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feeeb47db-3577-4204-a507-c34c1255fdbd_2000x1052.png 848w, https://substackcdn.com/image/fetch/$s_!_1pL!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feeeb47db-3577-4204-a507-c34c1255fdbd_2000x1052.png 1272w, https://substackcdn.com/image/fetch/$s_!_1pL!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feeeb47db-3577-4204-a507-c34c1255fdbd_2000x1052.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div><p><em>His site reports zero negative years across 2020&#8211;2026, and on his window we agree &#8212; zero of seven. Over the full history it is five negative years of fourteen. 2018 alone loses $30,107, and 2018 is entirely outside the tested period.</em></p><h2>The mechanism</h2><p><strong>You are paid least exactly when the risk is greatest</strong></p><p>The most useful thing in this whole exercise is not the drawdown number. It is the week-by-week shape of early 2020, which shows <em>how</em> strategies like this fail rather than merely that they can.</p><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!OC9Z!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff89b0928-5b75-4e40-9184-077c6fe30d38_1888x928.png 424w, https://substackcdn.com/image/fetch/$s_!OC9Z!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff89b0928-5b75-4e40-9184-077c6fe30d38_1888x928.png 848w, https://substackcdn.com/image/fetch/$s_!OC9Z!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff89b0928-5b75-4e40-9184-077c6fe30d38_1888x928.png 1272w, https://substackcdn.com/image/fetch/$s_!OC9Z!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff89b0928-5b75-4e40-9184-077c6fe30d38_1888x928.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!OC9Z!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff89b0928-5b75-4e40-9184-077c6fe30d38_1888x928.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/f89b0928-5b75-4e40-9184-077c6fe30d38_1888x928.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;February&#8211;April 2020, week by week&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="February&#8211;April 2020, week by week" title="February&#8211;April 2020, week by week" srcset="https://substackcdn.com/image/fetch/$s_!OC9Z!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff89b0928-5b75-4e40-9184-077c6fe30d38_1888x928.png 424w, https://substackcdn.com/image/fetch/$s_!OC9Z!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff89b0928-5b75-4e40-9184-077c6fe30d38_1888x928.png 848w, https://substackcdn.com/image/fetch/$s_!OC9Z!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff89b0928-5b75-4e40-9184-077c6fe30d38_1888x928.png 1272w, https://substackcdn.com/image/fetch/$s_!OC9Z!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff89b0928-5b75-4e40-9184-077c6fe30d38_1888x928.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div><p>The credit collected going into the crash was $134. The credit collected a month later, once the damage was done and volatility was enormous, was $375 &#8212; nearly triple, for weeks that all won comfortably.</p><p>Premium scales with volatility, and volatility is low right up until it isn't. So you are paid the least for taking the risk precisely when the risk is greatest, and paid the most afterwards, when the danger has passed. That is not misfortune. It is the defining structural property of selling volatility, and no amount of backtesting inside a calm window will reveal it.</p><h3>One quarter</h3><blockquote><p>February to April 2020 nets <strong>&#8722;$12,067</strong> on a single contract: three maximum losses in four weeks, each about $4,800. One quarter loses more than twice the entire claimed lifetime maximum drawdown.</p></blockquote><h2>Fairness</h2><p><strong>What this is not</strong></p><h3>Not a dishonesty finding</h3><p>He disclosed the start date, published every parameter down to the commission, and put the full specification on his own site. His arithmetic is sound and his win rate reproduces. He published a rule complete enough for a stranger to test &#8212; which is precisely why it could be tested at all. Most strategies that circulate with numbers attached cannot clear that bar, and the ones that cannot are the ones to worry about.</p><p>The criticism is narrower and it is about method, not character: six years is too short to price the tail of a strategy that earns small amounts often and loses large amounts rarely, and this particular window opens six weeks after the event that would have defined it.</p><h2>Method</h2><p><strong>How to check this</strong></p><h3>Rule</h3><p>Short strike = prior weekly close &#8722; weekly ATR(14), from the indicator's published source. Taken from his own published specification, not assumed: 50-point width, weekly SPXW expiry, entry first trading day around 10:00 ET, strike rounded to the nearest 5, hold to settlement, no stop or adjustment, $2.64 commission, skip the week if the natural credit is not positive.</p><div><hr></div><h3>Data and pricing</h3><p>Index history 2013&#8211;2026 from a gap-repaired 1-minute dataset resampled to weekly bars. No options data was purchased. The credit is the author's own stated $298 average, applied both as a constant and scaled to prevailing volatility, which brackets the realistic range.</p><div><hr></div><h3>Retail implementability &#8212; 9 / 12</h3><p>Weekly cadence, one liquid instrument, a single defined-risk order, ten minutes a week. Marked down for requiring options approval for spreads, and for demanding the discipline to accept a 16-to-1 loss-to-win ratio without intervening &#8212; and for a real drawdown that needs far more capital than the $4,605 figure implies.</p><div><hr></div><h3>Why we will not paper-trade it</h3><p>A six-month paper run would show roughly 95% wins and prove nothing &#8212; it would reproduce the exact flaw identified here. A strategy cannot be validated over a horizon shorter than the frequency of the losses that define it.</p><p><em>Historical simulation on index data with modelled option credits; not investment advice. Batch 02 of an ongoing verification series.</em></p>]]></content:encoded></item><item><title><![CDATA[The $25,000 Door]]></title><description><![CDATA[The $25,000 pattern-day-trader minimum is gone. The day-trading strategies it unlocks collapse under realistic slippage.]]></description><link>https://www.pastperformancelab.com/p/pdt-rule-replaced-day-trading-backtest</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/pdt-rule-replaced-day-trading-backtest</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Wed, 02 Sep 2026 08:00:00 GMT</pubDate><enclosure url="https://substack-post-media.s3.amazonaws.com/public/images/06154a9e-234c-46ee-bfb1-42ea1165e9c5_1688x336.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Updated 27 Sep 2026: the ATR trailing-stop figures are recomputed on NYSE trading sessions.</em></p><p><em>Updated 20 Sep 2026: we corrected the rule's start year from 1974 to 2001 and moved the broker-timeline note here.</em></p><p><em>Updated 16 Sep 2026: FINRA's rule took effect on 4 June 2026, but brokers have until 20 October 2027 to move accounts over. Your broker may still apply the $25,000 minimum. Under the new rules, repeatedly unmet intraday margin calls can restrict an account for up to 90 days. Source: <a href="https://www.finra.org/investors/insights/intraday-margin-requirements">FINRA</a>.</em></p><p><em>Rule change &#183; US retail brokerage &#183; 2 September 2026</em></p><p><em>For twenty-five years, a US trader with less than $25,000 could not legally day-trade more than three times in five business days. That rule is gone &#8212; and almost nobody has rewritten their strategy guidance for it.</em></p><h2>What changed</h2><p><strong>Pattern day trader, 2001&#8211;2026</strong></p><p>The pattern-day-trader rule required any margin account making four or more day trades in five business days to hold at least $25,000 in equity. Fall below it and the account was frozen to closing orders until it was topped up. It was introduced after the day-trading boom of the late 1990s, on the theory that frequent intraday trading warranted a higher capital cushion.</p><p>The SEC approved its elimination in April 2026. The $25,000 threshold is replaced by the ordinary $2,000 minimum for a margin account, with intraday buying power now set by each broker's own risk policy rather than a blanket federal floor.</p><p><strong>14 Apr 2026</strong> &#8212; SEC approves the rule change eliminating the pattern-day-trader designation and its $25,000 equity minimum.</p><p><strong>4 Jun 2026</strong> &#8212; Change takes effect.</p><p><strong>8 Jun 2026</strong> &#8212; Schwab stops counting day trades against client accounts.</p><p><strong>20 Oct 2027</strong> &#8212; Deadline for all brokers to complete implementation. Until then, individual brokers may still apply their own limits.</p><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!9dgp!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff65c6fc5-af5d-4b7d-b4ed-5f8813624e73_1688x336.png 424w, https://substackcdn.com/image/fetch/$s_!9dgp!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff65c6fc5-af5d-4b7d-b4ed-5f8813624e73_1688x336.png 848w, https://substackcdn.com/image/fetch/$s_!9dgp!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff65c6fc5-af5d-4b7d-b4ed-5f8813624e73_1688x336.png 1272w, https://substackcdn.com/image/fetch/$s_!9dgp!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff65c6fc5-af5d-4b7d-b4ed-5f8813624e73_1688x336.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!9dgp!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff65c6fc5-af5d-4b7d-b4ed-5f8813624e73_1688x336.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/f65c6fc5-af5d-4b7d-b4ed-5f8813624e73_1688x336.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Before: $25,000 minimum equity to day-trade freely in a US margin account; below it, three day trades per five business days, then a 90-day freeze. Now: a $2,000 standard margin-account minimum, with intraday buying power set by your broker.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Before: $25,000 minimum equity to day-trade freely in a US margin account; below it, three day trades per five business days, then a 90-day freeze. Now: a $2,000 standard margin-account minimum, with intraday buying power set by your broker." title="Before: $25,000 minimum equity to day-trade freely in a US margin account; below it, three day trades per five business days, then a 90-day freeze. Now: a $2,000 standard margin-account minimum, with intraday buying power set by your broker." srcset="https://substackcdn.com/image/fetch/$s_!9dgp!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff65c6fc5-af5d-4b7d-b4ed-5f8813624e73_1688x336.png 424w, https://substackcdn.com/image/fetch/$s_!9dgp!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff65c6fc5-af5d-4b7d-b4ed-5f8813624e73_1688x336.png 848w, https://substackcdn.com/image/fetch/$s_!9dgp!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff65c6fc5-af5d-4b7d-b4ed-5f8813624e73_1688x336.png 1272w, https://substackcdn.com/image/fetch/$s_!9dgp!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff65c6fc5-af5d-4b7d-b4ed-5f8813624e73_1688x336.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div><h2>Why it matters for strategy</h2><p><strong>A whole category of strategy was illegal for small accounts</strong></p><p>This is easy to under-rate as mere paperwork. It is not. It meant an entire family of published, widely taught strategies was unavailable to the readers most likely to be reading about them.</p><p>Take the 5-minute opening range breakout, one of the most-cited intraday strategies in retail circles. It takes roughly one trade per session, entering after the first five minutes and flat by the close &#8212; about 250 day trades a year. Under the old rule, running it in a US margin account below $25,000 was not merely inadvisable. It was a violation, and the account would have been frozen inside the first fortnight.</p><p>So for decades, guidance about intraday strategies came with an unstated asterisk: <em>this is for people who already have $25,000.</em> Most articles never said it. The strategies were presented as universally available when, for a large share of the audience, they were not.</p><h3>The part worth internalising</h3><blockquote><p>The constraint that made intraday strategies inaccessible to small accounts was regulatory, not economic &#8212; and it has been removed. Anyone re-evaluating an intraday strategy they dismissed years ago on capital grounds is now evaluating a genuinely different question.</p></blockquote><h2>What did not change</h2><p><strong>The rule was never the reason most people lost money</strong></p><p>It would be a poor reading of this to conclude that intraday trading just became a good idea for small accounts. The pattern-day-trader rule was a barrier. Removing a barrier does not create an edge behind it.</p><p>Everything that actually kills intraday strategies is untouched. Costs still scale with turnover, and turnover is exactly what intraday strategies have most of. In our own testing, <a href="https://pastperformancelab.substack.com/p/rsi2-orb-ut-bot-ttm-squeeze-backtest#&#167;ut-bot-atr-trailing-stop-fails-six-parameter-cells-tested">an ATR trailing-stop strategy on index futures</a> took 54,545 trades over thirteen years and lost about $940,000 per contract &#8212; not from being wrong about direction, but from being billed to death. The 5-minute ORB's <a href="https://pastperformancelab.substack.com/p/rsi2-orb-ut-bot-ttm-squeeze-backtest#&#167;5-minute-opening-range-breakout-fails-no-demonstrable-edge">published replication</a> collapses from $138,639 to $4,860 once two cents a share of slippage is applied. A gap filter we added later lifts it to a borderline edge, and the evidence for that edge disappears once fills arrive two minutes late (<a href="https://pastperformancelab.substack.com/p/backtest-vs-live-trading-47-second-delay">Issue 07</a>).</p><p>&#10003; <strong>You can now legally run an intraday strategy in a US margin account under $25,000.</strong><br><em>Subject to your broker's own implementation timeline, which may run to October 2027.</em></p><p>&#10005; <strong>Trading costs got cheaper.</strong><br><em>They did not. Cost per round trip is the single most common reason an intraday edge is imaginary.</em></p><p>&#10005; <strong>Smaller accounts became better suited to intraday trading.</strong><br><em>Fixed per-trade costs weigh proportionally heavier on small accounts, not lighter.</em></p><p>&#10005; <strong>The strategies themselves got better.</strong><br><em>A strategy that did not survive cost sensitivity before this rule change does not survive it now.</em></p><h3>Before you act on this</h3><p>Check what your own broker has actually implemented &#8212; the industry deadline is October 2027 and policies vary in the meantime. This applies to US margin accounts; cash accounts and non-US jurisdictions were never governed by this rule and are unaffected.</p><p>Then ask what we ask of every strategy we test, the Retail Gate: could someone with a day job, a broker and the published rules run it? If it needs paid data, an always-on computer or fills within seconds, the open door does not help you.</p><p>And the honest framing of the whole thing: a door opened. Nothing was said about what is on the other side of it.</p><h3>Your turn</h3><p>Send us the intraday strategy you are about to risk money on. Leave a comment or reply to any issue in your inbox. We test it and publish what we find.</p><p><em>Historical simulation figures cited are from our own backtests on index futures and from the published replication of the opening-range-breakout paper; they are not investment advice.<br>Sources: <a href="https://www.sec.gov/">SEC</a> rule approval April 2026, effective June 2026; broker implementation notices.</em></p>]]></content:encoded></item><item><title><![CDATA[Five Strategies, One Survivor]]></title><description><![CDATA[Five popular strategies rebuilt from their published rules and tested with costs. One survived. Issue 05 revisits it at the account level.]]></description><link>https://www.pastperformancelab.com/p/rsi2-orb-ut-bot-ttm-squeeze-backtest</link><guid isPermaLink="false">https://www.pastperformancelab.com/p/rsi2-orb-ut-bot-ttm-squeeze-backtest</guid><dc:creator><![CDATA[Antoni Gaudí]]></dc:creator><pubDate>Tue, 01 Sep 2026 09:00:00 GMT</pubDate><enclosure url="https://substack-post-media.s3.amazonaws.com/public/images/5eb5c14a-3e51-4c13-af96-d86678e3c03f_2080x1140.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>Updated 27 Sep 2026: figures recomputed on the NYSE trading calendar with a daily T-bill series. The verdicts are unchanged.</em></p><blockquote><p><em>Editor&#8217;s note, 3 September 2026. The Connors RSI(2) verdict in this issue was superseded the next day by Issue 05, The Winner That Doesn&#8217;t Win, which takes the strategy to the account level: per trade the edge is real, but in an account it makes 4.47% a year against buy-and-hold&#8217;s 12.71%. Read that issue first. The four failures here stand.</em></p></blockquote><p><em>Verification Batch 01 &#183; 1 September 2026 &#183; 13.7 years &#183; 1-minute bars</em></p><p><em>Popular trading strategies, reproduced from their published rules and run through the same pipeline on the same data. Four do not survive contact with costs, concentration, or a fair benchmark. One does &#8212; and its honest headline is smaller than its raw one.</em></p><p><strong>Instruments.</strong> US Tech 100 &#183; US 500</p><p><strong>Window.</strong> 2013-01 &#8594; 2026-08</p><p><strong>Bars tested.</strong> 9,437,100</p><p><strong>Sessions.</strong> 3,435 NYSE (US Tech 100) &#183; 3,365 NYSE (US 500)</p><h2>The ledger</h2><p><strong>What each strategy actually returned</strong></p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!R8uR!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F24d4db22-afa6-4d4e-9350-c53fcc44a4e3_1280x1398.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!R8uR!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F24d4db22-afa6-4d4e-9350-c53fcc44a4e3_1280x1398.png 424w, https://substackcdn.com/image/fetch/$s_!R8uR!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F24d4db22-afa6-4d4e-9350-c53fcc44a4e3_1280x1398.png 848w, https://substackcdn.com/image/fetch/$s_!R8uR!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F24d4db22-afa6-4d4e-9350-c53fcc44a4e3_1280x1398.png 1272w, https://substackcdn.com/image/fetch/$s_!R8uR!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F24d4db22-afa6-4d4e-9350-c53fcc44a4e3_1280x1398.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!R8uR!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F24d4db22-afa6-4d4e-9350-c53fcc44a4e3_1280x1398.png" width="1280" height="1398" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/24d4db22-afa6-4d4e-9350-c53fcc44a4e3_1280x1398.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1398,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:62218,&quot;alt&quot;:&quot;Table: verdict, profit factor, trades, net profit per contract, t-statistic and bootstrap p-value for seven strategy cells; only the two Connors RSI(2) cells survive.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Table: verdict, profit factor, trades, net profit per contract, t-statistic and bootstrap p-value for seven strategy cells; only the two Connors RSI(2) cells survive." title="Table: verdict, profit factor, trades, net profit per contract, t-statistic and bootstrap p-value for seven strategy cells; only the two Connors RSI(2) cells survive." srcset="https://substackcdn.com/image/fetch/$s_!R8uR!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F24d4db22-afa6-4d4e-9350-c53fcc44a4e3_1280x1398.png 424w, https://substackcdn.com/image/fetch/$s_!R8uR!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F24d4db22-afa6-4d4e-9350-c53fcc44a4e3_1280x1398.png 848w, https://substackcdn.com/image/fetch/$s_!R8uR!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F24d4db22-afa6-4d4e-9350-c53fcc44a4e3_1280x1398.png 1272w, https://substackcdn.com/image/fetch/$s_!R8uR!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F24d4db22-afa6-4d4e-9350-c53fcc44a4e3_1280x1398.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p><em>t-stat is on per-trade P&amp;L. Bootstrap p is the share of 2,000 stationary-block resamples of daily P&amp;L landing at or below zero. Net is one contract, no compounding, friction of 1 index point round trip on US Tech 100 and 0.3 on US 500.</em></p><h2>Control</h2><p><strong>Why you should believe the failures</strong></p><p>A pipeline that finds nothing is worthless if it would also find nothing in a strategy that works. So the first thing through it was a strategy already validated on a different engine, with a recorded result to hit &#8212; the Saty Phase Oscillator. This lab is new code on freshly downloaded data; it had to land on the old numbers independently.</p><h3>Independent reproduction &#183; Saty Phase Oscillator</h3><p>It landed. Maximum drawdown matched to the dollar and net P&amp;L to within 3.5%, from a separate download and a separately written engine. The suite was also run against synthetic random-walk data first: no strategy showed an edge, which is what rules out lookahead bias in the harness.</p><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!dbOW!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbf353225-7ae7-4605-ab00-1dd2d11ea9cf_542x342.png 424w, https://substackcdn.com/image/fetch/$s_!dbOW!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbf353225-7ae7-4605-ab00-1dd2d11ea9cf_542x342.png 848w, https://substackcdn.com/image/fetch/$s_!dbOW!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbf353225-7ae7-4605-ab00-1dd2d11ea9cf_542x342.png 1272w, https://substackcdn.com/image/fetch/$s_!dbOW!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbf353225-7ae7-4605-ab00-1dd2d11ea9cf_542x342.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!dbOW!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbf353225-7ae7-4605-ab00-1dd2d11ea9cf_542x342.png" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/bf353225-7ae7-4605-ab00-1dd2d11ea9cf_542x342.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:null,&quot;width&quot;:null,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;Reproduction parity table&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Reproduction parity table" title="Reproduction parity table" srcset="https://substackcdn.com/image/fetch/$s_!dbOW!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbf353225-7ae7-4605-ab00-1dd2d11ea9cf_542x342.png 424w, https://substackcdn.com/image/fetch/$s_!dbOW!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbf353225-7ae7-4605-ab00-1dd2d11ea9cf_542x342.png 848w, https://substackcdn.com/image/fetch/$s_!dbOW!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbf353225-7ae7-4605-ab00-1dd2d11ea9cf_542x342.png 1272w, https://substackcdn.com/image/fetch/$s_!dbOW!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fbf353225-7ae7-4605-ab00-1dd2d11ea9cf_542x342.png 1456w" sizes="100vw" loading="lazy"></picture><div></div></div></div><h2>Cost sensitivity</h2><p><strong>How much friction each edge can absorb</strong></p><p>Every strategy was re-priced at one, two and three times its assumed trading cost. The number below is the breakeven: the round-trip friction, in index points, at which the strategy's entire profit disappears. Anything close to real-world cost is not an edge, it is a rounding error that happened to land the right way.</p><p>Surviving cost is necessary but not sufficient &#8212; note that TTM Squeeze on daily bars tops this chart and still fails, because what kills it is concentration, not friction.</p><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!Th9v!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcfcf1254-2183-45a2-b4a5-b7a84f21f9b1_1280x1004.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!Th9v!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcfcf1254-2183-45a2-b4a5-b7a84f21f9b1_1280x1004.png 424w, https://substackcdn.com/image/fetch/$s_!Th9v!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcfcf1254-2183-45a2-b4a5-b7a84f21f9b1_1280x1004.png 848w, https://substackcdn.com/image/fetch/$s_!Th9v!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcfcf1254-2183-45a2-b4a5-b7a84f21f9b1_1280x1004.png 1272w, https://substackcdn.com/image/fetch/$s_!Th9v!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcfcf1254-2183-45a2-b4a5-b7a84f21f9b1_1280x1004.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!Th9v!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcfcf1254-2183-45a2-b4a5-b7a84f21f9b1_1280x1004.png" width="1280" height="1004" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/cfcf1254-2183-45a2-b4a5-b7a84f21f9b1_1280x1004.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:1004,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:36710,&quot;alt&quot;:&quot;Horizontal bar chart: breakeven friction in index points per round trip for eight strategies; the Connors RSI(2) cells clear the real cost of about one point by a wide margin, TTM Squeeze daily and the Nadaraya-Watson envelope are below zero.&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="Horizontal bar chart: breakeven friction in index points per round trip for eight strategies; the Connors RSI(2) cells clear the real cost of about one point by a wide margin, TTM Squeeze daily and the Nadaraya-Watson envelope are below zero." title="Horizontal bar chart: breakeven friction in index points per round trip for eight strategies; the Connors RSI(2) cells clear the real cost of about one point by a wide margin, TTM Squeeze daily and the Nadaraya-Watson envelope are below zero." srcset="https://substackcdn.com/image/fetch/$s_!Th9v!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcfcf1254-2183-45a2-b4a5-b7a84f21f9b1_1280x1004.png 424w, https://substackcdn.com/image/fetch/$s_!Th9v!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcfcf1254-2183-45a2-b4a5-b7a84f21f9b1_1280x1004.png 848w, https://substackcdn.com/image/fetch/$s_!Th9v!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcfcf1254-2183-45a2-b4a5-b7a84f21f9b1_1280x1004.png 1272w, https://substackcdn.com/image/fetch/$s_!Th9v!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcfcf1254-2183-45a2-b4a5-b7a84f21f9b1_1280x1004.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><p><em>A negative breakeven means the strategy loses money even with zero trading cost.</em></p><h2>Findings</h2><p><strong>What killed each one</strong></p><h3>Nadaraya-Watson envelope &#8212; Fails (significantly negative)</h3><p><strong>Win rate 57.5% &#183; Net &#8722;$298,139 &#183; t-stat &#8722;2.96 &#183; Breakeven friction &#8722;1.97 pts</strong></p><p>The cleanest negative result in the batch, and the most instructive. Nearly six trades in ten win &#8212; and it still loses a third of a million dollars per contract. The breakeven friction is negative, meaning it loses money at zero trading cost; the losers are simply far larger than the winners.</p><p>This is the single most useful thing on the page for anyone evaluating a strategy from a screenshot: <strong>win rate is not edge.</strong> A high win rate is the easiest statistic to show and the least informative one to see. Tested here in its non-repainting form, which is the honest version &#8212; the popular default repaints, and repainting flatters every backtest that includes it.</p><h3>TTM Squeeze &#8212; Fails (daily and 10-minute)</h3><p><strong>PF, daily 0.72 &#183; Net, daily &#8722;$41,766 &#183; Losing years 8 of 14 &#183; PF, 10-min 0.99</strong></p><p>On 10-minute bars it is nothing at all: profit factor 0.99, t-stat &#8722;0.15. On daily bars it loses outright: profit factor 0.72, t-stat &#8722;0.80, &#8722;$41,766 per contract, and 8 of 14 years negative.</p><p>Fifty-seven trades across nearly fourteen years is not a track record, it is a small sample with a good anecdote attached.</p><h3>UT Bot / ATR trailing stop &#8212; Fails (six parameter cells tested)</h3><p><strong>Best cell PF 1.05 &#183; Worst cell net &#8722;$937,728 &#183; Trades, worst cell 54,545 &#183; Breakeven friction 2.37 pts</strong></p><p>A friction machine. The aggressive setting takes 54,545 trades over the window and loses about $940,000 per contract &#8212; the strategy is not wrong about direction so much as it is billed to death. The best of the six cells reaches profit factor 1.05 with a t-stat of 1.32, which is indistinguishable from zero, and 52% of that profit sits in five trades.</p><p>At twice the assumed cost the best cell is already at breakeven. Sensitivity to a parameter you chose after seeing the results is the definition of a curve fit.</p><h3>5-minute Opening Range Breakout &#8212; Fails (no demonstrable edge)</h3><p><strong>PF 1.09 &#183; t-stat 1.41 &#183; Top 5 trades 49.8% of net &#183; 2026 YTD &#8722;$13,865</strong></p><p>Marginally positive on index futures and statistically indistinguishable from zero. The top five trades are about half of all profit, the best single year is another 36.5% of it, 5 of 14 years lose money, and the strategy is down on the year as of testing.</p><p>It survives cost better here than in its original form because index futures are cheap to trade relative to their point value. The published version is on QQQ shares, and an independent replication of that paper reports the result collapsing from $138,639 to $4,860 &#8212; Sharpe 1.06 down to 0.23, worse than buy-and-hold &#8212; once two cents per share of slippage is applied. The edge lives inside the spread.</p><h3>Connors RSI(2) &#8212; Survives (the one that holds up)</h3><p><strong>PF 2.67 &#183; t-stat 3.79 &#183; Breakeven friction 21.8 pts &#183; PF at 3&#215; cost 2.60</strong></p><p>It survives, and it survives on the dimensions that usually break things. The t-stat is 3.79 with a bootstrap p of 0.003. Breakeven friction is 21.8 points round trip against a real cost near one, so tripling the cost assumption moves profit factor from 2.67 only to 2.60. The profit is not concentrated &#8212; the top five trades are 27% of net, against 50% and 52% for the strategies above &#8212; and only four of thirteen years lose money.</p><p>Which brings us to the part that a chart of the equity curve would quietly leave out.</p><h2>The caveat</h2><p><strong>Connors does not beat buy-and-hold</strong></p><p>Connors RSI(2) is a long-only dip-buyer, tested across almost fourteen years in which the index roughly quadrupled. The benchmark that matters is not zero, it is owning the thing.</p><p>&#10005; <strong>&#8220;Connors RSI(2) returned $115,925 per contract.&#8221;</strong><br><em>True, and misleading. Buy-and-hold over the same window returned $291,484 &#8212; more than double.</em></p><p>&#10005; <strong>&#8220;Roughly 3&#215; the return per unit of market exposure, at a fifth of the drawdown.&#8221;</strong><br><em>The strategy is in the market 11.7% of the time. Exposure-matched, buy-and-hold returns $33,969 against Connors' $115,925, but the worst drawdown is &#8722;$19,710 against &#8722;$60,978, about a third, not a fifth. And in an account it makes 4.47% a year against 12.71% (Issue 05).</em></p><h3>Stated in the same breath, not the footnotes</h3><blockquote><p>Two further limits belong with any use of this result. Entries and exits are taken at the signal day's close, which assumes you can transact at the close &#8212; a real implementation will not match the backtest exactly. And the test runs on a CFD proxy for the index rather than the cash instrument.</p><p>None of that makes the edge disappear. It does mean the honest claim is narrower than the raw number, and anyone printing the raw number beside an equity curve is misleading by omission.</p></blockquote><h2>Method</h2><p><strong>How to check this</strong></p><h3>Data</h3><p>Dukascopy 1-minute bid bars, 2013-01-01 to 2026-08-31, restricted to NYSE trading sessions: 4,767,120 bars across 3,435 sessions on US Tech 100, and 4,669,980 bars across 3,365 sessions on US 500. The binary decoder's field order was validated at 100% open-high-low-close consistency rather than assumed.</p><div><hr></div><h3>Conventions</h3><p>Identical across every strategy, and identical to the engine used for the control: the signal is evaluated on the bar close, the fill is taken at the next bar's open, day strategies are flat at 16:00 ET, and indicators use Pine-compatible seeding so that a TradingView reader sees the same values. Friction is 1 index point round trip on US Tech 100 and 0.3 on US 500, swept at 1&#215;, 2&#215; and 3&#215;.</p><div><hr></div><h3>Checks run before any result was read</h3><p>The full suite was executed against synthetic random-walk data, where no strategy should show an edge. None did. Trade-accounting invariants were asserted mechanically: entry windows respected, no overnight holds in day strategies, points/dollars/friction internally consistent, and stop-loss exits never recorded as profitable.</p><div><hr></div><h3>Reproducing it</h3><p>Engine, verification pass, data loaders and per-strategy trade logs live in <code>/root/stratlab</code>, kept separate from the live paper-trading service. Every number on this page traces to <code>out/results.json</code> or <code>out/verify.json</code>.</p><p><em>Verification batch 01 &#183; seven configurations tested across five strategies &#183; one survivor, stated with its caveats.<br>Results are historical simulation on proxy data and are not investment advice.</em></p>]]></content:encoded></item></channel></rss>