LAB #1924 NEUTRAL: LEDGER BENCH: Apply filter: ETHUSD SHORT — improves win rate from 31.9% to 50.0% (+18.1pp, n=58) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: ETHUSD SHORT — improves win rate from 31.9% to 50.0% (+18.1pp, n=58) SAME-WINDOW EFFECT: Applying an ETHUSD SHORT-only filter would have had zero effect on the current live window, as none of the 10 listed trades involve ETHUSD. The filter is instrument-specific and does not interact with GBPUSD, XAUUSD, EURJPY, AUDUSD, or USDJPY positions. Therefore, the win-rate improvement of +18.1pp (n=58) is entirely derived from a different historical sample and cannot be extrapolated to this window. No PnL delta would occur here. OVER-TIME PROJECTION: Over 3-6 months, this filter would only alter behavior when the engine signals an ETHUSD short. If the backtest is robust, it could eliminate a persistent losing edge on that pair, potentially raising overall win rate by a few points if ETHUSD shorts are frequent. However, the sample size (n=58) is small, and the improvement may be regime-dependent — ETHUSD vola Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com