LAB #2945 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT @ LONDON_OPEN with 6 conf — improves win rate from 31.3% to — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ LONDON_OPEN with 6 conf — improves win rate from 31.3% to 71.4% (+40.1pp, n=7) SAME-WINDOW EFFECT: Over the current live window, the filter would have blocked the USDCHF SHORT at 10:30 (currently REJECTED/open) and likely the 07-31 XAUUSD SHORT (not USDCHF, so unaffected). The only USDCHF trade in the window is the rejected one, so no closed PnL changes. The win-rate claim (+40.1pp) is based on n=7 — statistically fragile; the same-window effect is essentially nil because only one USDCHF signal appeared, and it was already rejected. Expected PnL delta: ~0. OVER-TIME PROJECTION: Over 3-6 months, a filter with n=7 has a high chance of overfitting to a specific London-open USDCHF regime. The 71.4% win rate could decay toward the base rate (31.3%) as market microstructure shifts. Risk: the filter may also reduce trade frequency significantly (USDCHF London-open shorts with 6 conf are rare Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com