LAB #849 PROMISING: LEDGER BENCH: Apply filter: USDCHF SHORT @ NY_OPEN with 5 conf — improves win rate from 31.5% to 64. — E8 Intelligence Research

Abstract

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ NY_OPEN with 5 conf — improves win rate from 31.5% to 64.2% (+32.6pp, n=67) SAME-WINDOW EFFECT: Over the current trade window, the USDCHF SHORT via rizzy5m entry at 0.81212 (CLOSED/WIN) would have been unaffected because it entered at 09:05, not NY_OPEN. No other trades in the window are USDCHF SHORT at NY_OPEN, so zero trades would have been added or removed. The win-rate delta is 0% for this specific window, and PnL unchanged. OVER-TIME PROJECTION: The claimed +32.6pp win-rate improvement on n=67 is statistically significant but likely overfitted to a specific market regime (e.g., USD strength at NY open during a particular volatility cluster). Over 3-6 months, the filter may degrade as seasonality shifts, and the small sample size (67) raises risk of false discovery. Expect win-rate to regress toward 45-50% in live running, with risk of missing profitable USDCHF shorts outside NY_O Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com