LAB #3997 PROMISING: LEDGER BENCH: Apply filter: XAUUSD LONG — improves win rate from 32.5% to 55.4% (+23.0pp, n=83) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD LONG — improves win rate from 32.5% to 55.4% (+23.0pp, n=83) SAME-WINDOW EFFECT: Applying the XAUUSD LONG-only filter would have blocked the single XAUUSD SHORT trade in the live window (entry 4598.79, CLOSED/LOSS), removing one loss from the sample. That trade was a loss, so the win rate in this small window would improve from 4 wins/10 trades (40%) to 4 wins/9 trades (44.4%), a modest +4.4pp. PnL delta is small but positive — you avoid one losing trade, but no new wins are added. The filter does not affect any other instrument or direction in this window, so the broader impact here is minimal. OVER-TIME PROJECTION: Over 3-6 months, the filter would eliminate all XAUUSD SHORT entries, which historically have a 32.5% win rate — that is a clear drag. If the backtest holds, you would see a meaningful lift in overall win rate, but the sample (n=83) is small and the improvement could be regime-de Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com