LAB #2084 NEUTRAL: LEDGER BENCH: Apply filter: EURUSD LONG — improves win rate from 32.0% to 35.6% (+3.5pp, n=45) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: EURUSD LONG — improves win rate from 32.0% to 35.6% (+3.5pp, n=45) SAME-WINDOW EFFECT: Applying a EURUSD LONG-only filter would have excluded zero of the ten listed trades, as none are EURUSD. Therefore, no direct PnL or win-rate change occurs in this specific window. The claimed +3.5pp win-rate improvement (n=45) is not observable here, so the live impact is nil for this sample. The filter's benefit, if real, would only appear in a larger EURUSD-specific subset, which this window lacks. OVER-TIME PROJECTION: Over 3-6 months, a EURUSD LONG filter could reduce trade frequency and concentrate risk on a single pair's long bias. If the backtest's +3.5pp is statistically robust (n=45 is small, margin of error ~±14pp at 95% CI), it might lift overall win rate slightly, but it also risks missing EURUSD short opportunities that could be profitable. The main risk is overfitting to a short, favorable period; Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com