Machine Learning on FX Backtest Diaryhttps://etherpoc.com/en/tags/machine-learning/Recent content in Machine Learning on FX Backtest DiaryHugoenFri, 24 Jul 2026 00:00:00 +0000A +33.8% backtest fell to -3.0% in walk-forward: all three roads to complexity failedhttps://etherpoc.com/en/posts/indicator-stacking/Fri, 24 Jul 2026 00:00:00 +0000https://etherpoc.com/en/posts/indicator-stacking/<p>Over the full test period the numbers read +33.8% with a PF of 1.15. For a moment I thought I had finally found it. Then the walk-forward test came back: -3.0% overall, profitable in one year out of five. Gone.</p> <p>This article merges five studies (research notes 34, 44, 45, 47 and 61) into one story about complexity. I attacked the market from three directions that every trader eventually tries: let machine learning dig through a mountain of features, stack indicators on top of each other (a fractal base, fractals plus filters, then a multi-timeframe combo), and shrink the timeframe for more trades. All three roads ended in rejection. But the five studies failed in exactly the same shape, and that shape is worth more than any single result.</p>My AI position sizer lost to a shuffled placebo, and six more smart ideas died with ithttps://etherpoc.com/en/posts/smart-sizing-placebo/Fri, 24 Jul 2026 00:00:00 +0000https://etherpoc.com/en/posts/smart-sizing-placebo/<p>A reinforcement learner studied my trading system&rsquo;s history and carefully learned how much leverage to use in each market state. Its result: +0.72% per month. Then I took its learned rules, shuffled them into deliberate nonsense, and ran the test again: +1.57% per month. The intelligence was worth less than nothing.</p>Measuring 'it comes down to discretion' to death: 88 conditions and an AI eyehttps://etherpoc.com/en/posts/discretion-final/Tue, 21 Jul 2026 00:00:00 +0000https://etherpoc.com/en/posts/discretion-final/<p>Every strategy video has the same closing line: &ldquo;in the end, it comes down to discretion&rdquo;. Show mechanically that the rules lose, and this one sentence resets the whole debate. Discretion cannot be put into words, therefore cannot be measured, therefore cannot be refuted. So the story goes.</p> <p>Does it hold? I decided discretion becomes measurable the moment you redefine it as information: the ability to select better-than-average trades out of a candidate stream. Then I measured every route that information could travel: 88 verbalizable conditions, cross-market context, the entire multi-timeframe combination space, machine learning, state-of-the-art vision AI, and my own blind-test performance.</p>