LAB #2850 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG @ NY_OPEN with 6 conf — improves win rate from 31.1% to 64.7 — 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 31.1% to 64.7% (+33.6pp, n=17) SAME-WINDOW EFFECT: Over the current live window, applying the USDCHF LONG @ NY_OPEN + 6-conf filter would have blocked the only USDCHF trade (SHORT, rejected/open) — no direct win-rate change since no USDCHF LONG was taken. However, the filter's logic (long-only, NY_OPEN, high confidence) would not have altered any of the other 9 trades (GBPUSD, XAUUSD, AUDUSD, USDCAD, USDJPY), so the realized win rate (6/9 = 66.7%) and PnL would remain identical. The claimed +33.6pp improvement comes from a different historical subset (n=17), not this window — so no measurable delta here. OVER-TIME PROJECTION: Over 3–6 months, a long-only USDCHF filter at NY_OPEN with 6 conf could exploit a persistent intraday bias if the backtest is robust, but the tiny sample (n=17) and extreme win-rate jump (31.1%→64.7%) suggest overfittin Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com