LAB #2900 NEUTRAL: LEDGER BENCH: Apply filter: EURUSD LONG — improves win rate from 31.1% 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 31.1% 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 no EURUSD trades appear in the GTX setup results. The +3.6pp win-rate improvement (31.1%→34.8%) is derived from a separate backtest population (n=46), not this window. Therefore, the live PnL delta over this specific window is exactly $0. The filter would neither help nor hurt current open/closed positions. OVER-TIME PROJECTION: Over 3–6 months, the filter could add ~3–4pp win rate if the EURUSD LONG edge persists, but the sample (n=46) is small and likely overfit to a specific regime (e.g., dollar weakness or carry dynamics). The main risk is selection bias: filtering only EURUSD LONG may reduce trade frequency (fewer setups), lowering total PnL even if win rate rises, especially if Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com