LAB #3879 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT @ NY_OPEN with 5 conf — improves win rate from 32.5% to 64. — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ NY_OPEN with 5 conf — improves win rate from 32.5% to 64.2% (+31.7pp, n=67) SAME-WINDOW EFFECT: Over the current live window, this filter would have blocked the USDCHF LONG via rizzy7m (0.80231, closed/loss) and likely the USDCHF-related short entries if any existed — but none did. The only USDCHF trade in the window was a long, which the filter (SHORT-only) would not have blocked, so no direct PnL change from that trade. However, the filter's 5-conf requirement would have rejected the NZDUSD SHORT (rizzy5m, loss) and possibly the XAUUSD SHORT (rizzy5m, loss) if their confidence scores were below 5 — but we lack per-trade conf data. Net expected delta: minimal to slightly positive, likely +0.5–1.5% PnL over the window if it filtered 1–2 losing shorts, but no win-rate shift since no USDCHF short was taken. OVER-TIME PROJECTION: Over 3–6 months, this filter would restrict entries to a s Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com