LAB #2355 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG @ NY_OPEN with 6 conf — improves win rate from 31.2% to 62.5 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF LONG @ NY_OPEN with 6 conf — improves win rate from 31.2% to 62.5% (+31.3pp, n=16) SAME-WINDOW EFFECT: Over the current 10-trade window, this filter would have had zero direct impact — no USDCHF trades are present, so the live PnL and win rate (5W/5L) would remain unchanged. The claimed +31.3pp win-rate improvement is derived from a tiny n=16 backtest subset, which is statistically fragile; a single trade flip changes the result by ~6pp. If the filter had been active, it would only have suppressed potential USDCHF LONG entries at NY_OPEN with conf=6 — none occurred here, so no trades affected. The real risk is that this filter may be overfit to a narrow regime (likely August 2026 volatility) and could silently block profitable USDCHF longs in other conditions. OVER-TIME PROJECTION: Over 3–6 months, this filter could improve USDCHF-specific win rate if the edge is real, but the sample size (n= Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com