LAB #2363 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD LONG @ ASIAN with 5 conf — improves win rate from 31.2% to 66.7% — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD LONG @ ASIAN with 5 conf — improves win rate from 31.2% to 66.7% (+35.5pp, n=21) SAME-WINDOW EFFECT: Applying this filter would have blocked the XAUUSD SHORT entries on 2026-07-31 (both 09:55 and 11:20) and the XAUUSD SHORT on 2026-08-04, all of which were losses. It would also have blocked the XAUUSD LONG via rizzy7m on 2026-08-06 — which was a WIN — so you would have sacrificed one profitable trade to avoid three losers. Net PnL delta: +2 wins avoided (losses) minus 1 win sacrificed, roughly +1.5R improvement on this window, but the win-rate metric is misleading because it excludes the sacrificed winner. OVER-TIME PROJECTION: Over 3-6 months, this filter will likely reduce XAUUSD trade frequency by ~40-50% and shift the remaining sample toward Asian-session, high-confidence setups. The risk is overfitting to a tiny n=21 sample — the +35.5pp jump is statistically fragile (95% CI roughly 44% Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com