LAB #346 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT @ LONDON_OPEN with 5 conf — improves win rate from 32.4% to — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ LONDON_OPEN with 5 conf — improves win rate from 32.4% to 62.5% (+30.1pp, n=16) SAME-WINDOW EFFECT: The USDCHF SHORT @ LONDON_OPEN with 5 conf filter would have directly affected the live USDCHF SHORT via rizzy5m entry at 0.81212 on 2026-07-22 09:05:00+02:00. Since this trade was already a WIN, the filter would not have prevented it, but it would have added a confirmation layer that might have delayed or altered the entry timing. No other trades in the window are USDCHF SHORT at London Open, so the net PnL delta is zero for this specific window. The win-rate improvement claim (+30.1pp) is based on only 16 samples, which is statistically weak and likely overfitted to a specific period. OVER-TIME PROJECTION: Over 3-6 months, applying this filter could modestly improve win rate if the London Open USDCHF short pattern is genuine, but the small sample size (n=16) means high variance and ri Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com