LAB #4000 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT — improves win rate from 32.5% to 54.0% (+21.5pp, n=263) — E8 Intelligence Research

Abstract

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT — improves win rate from 32.5% to 54.0% (+21.5pp, n=263) SAME-WINDOW EFFECT: Applying a USDCHF SHORT-only filter would have excluded the single USDCHF LONG trade (entry 0.80231, CLOSED/LOSS) from the live window — a direct removal of a losing trade. It would not have affected any other listed pairs, so the immediate win-rate delta is marginal (removing 1 loss from 10 trades shifts win rate from 30% to 33.3%, not the claimed +21.5pp). The backtest's +21.5pp improvement appears to be driven by a broader historical sample, not this specific window, so the live PnL delta here is roughly +0.5R (avoiding one loss) — negligible. OVER-TIME PROJECTION: Over 3-6 months, a USDCHF SHORT filter could plausibly improve win rate if the pair's short-side behavior is structurally different (e.g., trend persistence or spread/rollover asymmetries). However, the risk is overfitting to a 263-trade sample — Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com