LAB #1823 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD LONG @ ASIAN with 5 conf — improves win rate from 31.9% to 66.7% — E8 Intelligence Research

Abstract

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD LONG @ ASIAN with 5 conf — improves win rate from 31.9% to 66.7% (+34.7pp, n=21) SAME-WINDOW EFFECT: Applying the XAUUSD LONG @ ASIAN + 5-conf filter would have blocked the two XAUUSD SHORT losses (entries at 4051.79 and 4066.35) since they are shorts, not longs — so those two losing trades would be removed from the window. However, it would not have added any new trades, as no XAUUSD LONG entries appear in the live list. The net effect on this specific window is a PnL improvement of roughly +2R (assuming typical stop-loss distance), but the win-rate calculation is misleading because the filter only removes losing shorts, not because it predicts long direction better. The 66.7% win rate on n=21 is statistically fragile — a single loss flips it to 62%, and the sample is too small to separate regime luck from signal. OVER-TIME PROJECTION: Over 3-6 months, this filter would likely reduce trade f Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com