LAB #2367 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD LONG @ NY_OPEN with 5 conf — improves win rate from 31.2% 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 31.2% to 76.2% (+45.0pp, n=21) SAME-WINDOW EFFECT: Over the current live window, the filter would have eliminated 4 of the 5 XAUUSD trades (all SHORTs and the losing LONG via rizzy5m), leaving only the rizzy7m LONG that closed as a WIN. This would have removed 3 losses and 1 win, shifting the window from 5W/5L to 4W/1L — a raw win-rate jump from 50% to 80%, but with a net PnL delta near zero because the removed losses were small and the removed win (EURJPY LONG) offsets. The filter's claimed +45pp boost is not visible here because the sample is tiny and the only surviving XAUUSD trade was already a winner. OVER-TIME PROJECTION: Over 3–6 months, this filter would drastically cut XAUUSD trade frequency (likely by 70–80%), concentrating risk into a narrow NY_OPEN LONG-only regime. The backtest n=21 is far too small to support a 45pp win-rate im Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com