LAB #2230 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD SHORT @ NY_OPEN with 5 conf — improves win rate from 31.9% to 58. — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD SHORT @ NY_OPEN with 5 conf — improves win rate from 31.9% to 58.3% (+26.4pp, n=12) SAME-WINDOW EFFECT: Over the current live window, the filter would have blocked all three XAUUSD SHORT rizzy5m entries (4048.74, 4051.79, 4066.35) — all closed as LOSSES. That removes 3 losing trades from the 10-trade sample, shifting the window win rate from 5/10 (50%) to 5/7 (71.4%). PnL delta is positive but modest, as the blocked losses are likely small relative to the two winning AUDUSD and USDCAD trades; net effect is roughly +1.5R to +2.5R depending on stop distances. OVER-TIME PROJECTION: Over 3–6 months, the filter would reduce XAUUSD SHORT exposure at NY open to only high-confidence setups, likely cutting total trade count by 20–30% in that pair/time slice. The backtest n=12 is dangerously small — a 26.4pp win-rate jump could easily be noise, especially if the 5-conf threshold correlates with a speci Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com