LAB #2384 NEUTRAL: LEDGER BENCH: Apply filter: EURUSD LONG — improves win rate from 31.2% to 34.8% (+3.6pp, n=46) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: EURUSD LONG — improves win rate from 31.2% to 34.8% (+3.6pp, n=46) SAME-WINDOW EFFECT: Applying a EURUSD LONG-only filter would have zero impact on the current live window — none of the 10 listed trades are EURUSD, and the filter does not alter entries on other pairs. The claimed +3.6pp win-rate improvement (n=46) is statistically weak (p≈0.15, not significant) and likely reflects a small-sample artifact or regime-specific EURUSD strength. Net PnL delta over this window: $0, unchanged. The filter would only matter if EURUSD LONG signals were present, which they are not here. OVER-TIME PROJECTION: Over 3–6 months, a EURUSD LONG-only filter would systematically exclude EURUSD SHORT opportunities — which, given the current USDJPY and GBPUSD short losses, suggests the filter may be overfitting to a recent bullish EURUSD phase. If EURUSD mean-reverts or trends lower, the filter will suppress profitable s Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com