LAB #1868 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG — improves win rate from 32.0% to 35.6% (+3.6pp, n=90) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF LONG — improves win rate from 32.0% to 35.6% (+3.6pp, n=90) SAME-WINDOW EFFECT: Applying a USDCHF LONG-only filter would have had zero direct impact on the current live window, as none of the 10 listed trades are USDCHF. However, the filter would have suppressed any potential USDCHF LONG signals that might have been generated but were not recorded here — meaning no PnL delta in this specific window. The only indirect effect is a slight reduction in total trade count (if any USDCHF LONGs were skipped), which could marginally lower variance but not alter the win rate of the existing non-USDCHF trades. Expected win-rate change in this window: 0.0pp; PnL delta: ~0. OVER-TIME PROJECTION: Over 3–6 months, a USDCHF LONG-only filter would concentrate the model on a single pair-direction, which historically shows a +3.6pp win-rate improvement (32.0%→35.6%) on n=90. The risk is overfitting to a short, Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com