LAB #850 PROMISING: LEDGER BENCH: Apply filter: XAUUSD LONG @ NY_OPEN with 5 conf — improves win rate from 31.5% to 76.2 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD LONG @ NY_OPEN with 5 conf — improves win rate from 31.5% to 76.2% (+44.6pp, n=21) SAME-WINDOW EFFECT: Over the current trade window, applying this filter would have rejected the XAUUSD SHORT entry at 4100.865 (currently REJECTED/open), which is consistent with the filter's LONG-only bias at NY_OPEN. No other trades in the window are directly affected since none are XAUUSD LONG entries at NY_OPEN with 5 conf. The net PnL delta is zero for this specific window, as the filter would not have altered any closed trade outcomes. However, the filter's absence means a potential XAUUSD LONG opportunity at NY_OPEN with 5 conf was not captured, leaving a possible missed win. OVER-TIME PROJECTION: Over 3-6 months, this filter could significantly boost XAUUSD-specific win rate from ~31.5% to ~76.2%, but the sample size of 21 is dangerously small — a single outlier trade could skew results by 5 percentage Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com