LAB #978 PROMISING: LEDGER BENCH: Apply filter: USDCHF SHORT @ NY_OPEN with 5 conf — improves win rate from 31.6% 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 31.6% to 64.2% (+32.5pp, n=67) SAME-WINDOW EFFECT: Over the current live trade window, the USDCHF SHORT via rizzy5m entry at 0.81212 on 2026-07-22 09:05 was already a CLOSED/WIN. Applying the NY_OPEN + 5 conf filter would have rejected this trade since it entered at 09:05, not NY_OPEN (typically 14:00 UTC). This would have removed one win from the window, reducing the win count by 1 and slightly lowering the overall win rate for that period. No other trades in the window are USDCHF SHORT, so the net PnL delta is negative for this specific sample. OVER-TIME PROJECTION: Over 3-6 months, this filter could meaningfully improve win rate on USDCHF SHORT trades from ~32% to ~64%, but only if the backtest sample (n=67) is representative and not overfitted to a specific market regime. Risk includes reduced trade frequency (fewer USDCHF SHORT entries Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com