LAB #437 PROMISING: LEDGER BENCH: Apply filter: USDCHF SHORT — improves win rate from 32.4% to 62.7% (+30.4pp, n=161) — E8 Intelligence Research

Abstract

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT — improves win rate from 32.4% to 62.7% (+30.4pp, n=161) SAME-WINDOW EFFECT: Over the current trade window, applying the USDCHF SHORT filter would have blocked the one USDCHF SHORT trade listed (rizzy5m entry=0.81212, CLOSED/WIN). This trade was a winner, so the filter would have removed a winning trade, reducing the window's win count by 1 and slightly lowering the overall win rate. The net PnL delta would be negative, as a profitable trade is excluded, but the sample is too small to draw meaningful conclusions. OVER-TIME PROJECTION: Over 3-6 months, the filter's claimed +30.4pp win rate improvement (n=161) suggests it effectively eliminates many losing USDCHF SHORT trades. However, it may also filter out some winners, potentially reducing total trade frequency and overall PnL if the win rate gain is offset by fewer opportunities. Risks include overfitting to the backtest period, espec Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com