LAB #1240 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT @ ASIAN with 5 conf — improves win rate from 31.5% to 63.2% — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ ASIAN with 5 conf — improves win rate from 31.5% to 63.2% (+31.6pp, n=19) SAME-WINDOW EFFECT: Over the current trade window, this filter would have blocked the USDCHF SHORT via rizzy5m entry=0.81212 (CLOSED/WIN), removing a winning trade. It would also have prevented any other USDCHF SHORT entries during Asian hours with confidence 5, but no other such trades appear in the window. The net effect is a loss of one win, reducing the window's win count by 1 and slightly lowering PnL. Given the small sample (n=19 in backtest), the live impact is negligible but directionally negative here. OVER-TIME PROJECTION: Over 3-6 months, the filter claims a +31.6pp win rate improvement from a tiny sample (n=19), which is statistically unreliable — likely overfitting to a specific period. The risk is that Asian-session USDCHF SHORTs with conf 5 may have been coincidentally favorable in that backtest w Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com