LAB #2216 NEUTRAL: LEDGER BENCH: Apply filter: GBPUSD LONG — improves win rate from 31.9% to 39.1% (+7.3pp, n=46) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: GBPUSD LONG — improves win rate from 31.9% to 39.1% (+7.3pp, n=46) SAME-WINDOW EFFECT: Over the current live window, applying a GBPUSD LONG-only filter would have blocked the two GBPUSD SHORT trades (both losses) and allowed the one GBPUSD LONG (a win). That removes 2 losses and keeps 1 win, shifting the window from 4W/5L to 5W/3L — a raw win-rate improvement of ~11pp on this small sample. PnL delta is positive but modest: you avoid two losing shorts and keep one winning long, roughly +1.2R net if losses were ~1R each. However, the filter also blocks any future GBPUSD SHORT that might win — the backtest n=46 is too small to trust the +7.3pp as stable. OVER-TIME PROJECTION: Over 3–6 months, a single-pair directional filter risks overfitting to a specific regime (e.g., GBP strength during that backtest window). If GBPUSD mean-reverts or trends down, you'll miss profitable shorts and the win-rate gain Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com