LAB #4435 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT @ OFF_SESSION with 6 conf — improves win rate from 31.5% to — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ OFF_SESSION with 6 conf — improves win rate from 31.5% to 66.7% (+35.1pp, n=6) SAME-WINDOW EFFECT: Over the current live window, no USDCHF SHORT trades appear in the list, so this filter would have changed nothing in the observed trades. The claimed improvement (+35.1pp) is based on only 6 backtested samples, which is statistically fragile — a single loss flips the win rate to 50%, and two losses drop it below the baseline. The live window shows no USDCHF SHORT entries at all, meaning the filter is currently irrelevant to actual execution flow. Expected PnL delta in this window: $0. OVER-TIME PROJECTION: Over 3–6 months, this filter would likely reduce trade frequency on USDCHF SHORTs during off-session hours, potentially avoiding some losses but also missing occasional winners. The core risk is overfitting to a tiny sample (n=6) — the 66.7% win rate has a 95% confidence interval roug

Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com