LAB #2999 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG — improves win rate from 31.3% to 37.1% (+5.8pp, n=97) — E8 Intelligence Research

Abstract

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF LONG — improves win rate from 31.3% to 37.1% (+5.8pp, n=97) SAME-WINDOW EFFECT: Applying a USDCHF LONG-only filter would have blocked the single USDCHF SHORT trade in the window (entry 0.81122, currently rejected/open). That trade is not yet resolved, so the immediate PnL impact is unknown but likely neutral-to-positive if it would have lost. No other trades involve USDCHF, so win rate among the 9 resolved trades stays at 5/9 (55.6%) — unchanged. The filter adds no benefit here; it only removes one open position from consideration. OVER-TIME PROJECTION: Over 3–6 months, a +5.8pp win-rate improvement on USDCHF longs (n=97) is statistically weak — the sample is small and the gain could be noise. The filter would also eliminate all USDCHF shorts, which may have asymmetric tail risk (CHF intervention spikes). If the edge is real, it likely comes from a specific regime (e.g., risk-on USD strength) Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com