LAB #2892 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT @ NY_OPEN with 5 conf — improves win rate from 31.1% to 64. — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ NY_OPEN with 5 conf — improves win rate from 31.1% to 64.2% (+33.0pp, n=67) SAME-WINDOW EFFECT: Over the current live window, the filter would have blocked the USDCHF SHORT entry at 10:30 (currently REJECTED/open) — no PnL change there. It would also have blocked the USDCHF SHORT at 11:35 if it had fired (it didn't, but the filter would suppress any USDCHF shorts at NY_OPEN with <5 conf). The only other USDCHF trade in the window is absent, so the immediate effect is neutral — no wins or losses removed. The claimed +33pp win-rate improvement is based on n=67 backtest trades, but the live window contains zero qualifying USDCHF SHORTs at NY_OPEN with 5 conf, so the delta is unobservable here. OVER-TIME PROJECTION: Over 3–6 months, if the filter is real, it would eliminate a subset of low-confidence USDCHF shorts that historically lose ~69% of the time. However, the sample (n=67) is smal Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com