LAB #2849 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG — improves win rate from 31.1% to 37.5% (+6.4pp, n=96) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF LONG — improves win rate from 31.1% to 37.5% (+6.4pp, n=96) SAME-WINDOW EFFECT: Applying a USDCHF LONG-only filter would have blocked the one USDCHF SHORT trade (entry=0.81122, currently open/rejected) — that trade is not yet resolved, so no immediate win/loss delta is certain. However, if that SHORT had been closed as a loss (consistent with the broader USDCHF SHORT underperformance), the filter would have avoided that negative PnL. The other nine trades (GBPUSD, XAUUSD, AUDUSD, USDCAD, USDJPY) are unaffected, so the net same-window effect is neutral-to-slightly positive, depending on the open USDCHF outcome. The +6.4pp win-rate improvement is not visible in this small sample because only one USDCHF trade appears. OVER-TIME PROJECTION: Over 3–6 months, a USDCHF LONG-only filter could plausibly lift overall win rate if the historical edge is real, but the sample (n=96) is thin and the +6.4pp Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com