LAB #4063 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG — improves win rate from 32.5% to 39.2% (+6.6pp, n=143) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF LONG — improves win rate from 32.5% to 39.2% (+6.6pp, n=143) SAME-WINDOW EFFECT: Over the current live window, the USDCHF LONG filter would have had zero direct impact — none of the 10 listed trades are USDCHF. The claimed +6.6pp win-rate improvement (n=143) is statistically weak (p≈0.15, not significant at 95% CI), and the filter would not have blocked or altered any of the existing GBPUSD, USDJPY, NZDUSD, AUDUSD, XAUUSD, or EURJPY trades. PnL delta over this window: $0. The filter is orthogonal to current exposure, so it neither helps nor hurts here — but it also provides no evidence of live efficacy. OVER-TIME PROJECTION: Over 3–6 months, adding a USDCHF LONG filter would likely reduce trade frequency (fewer USDCHF longs) while marginally improving win rate if the backtest edge is real — but the small sample (n=143) and the fact that USDCHF is a low-volatility, trend-poor pair make overfit Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com