LAB #2604 NEUTRAL: LEDGER BENCH: Apply filter: ETHUSD SHORT — improves win rate from 31.0% to 50.8% (+19.8pp, n=59) — E8 Intelligence Research

Abstract

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: ETHUSD SHORT — improves win rate from 31.0% to 50.8% (+19.8pp, n=59) SAME-WINDOW EFFECT: Applying the ETHUSD SHORT filter would have zero effect on the current live window — none of the 10 listed trades involve ETHUSD. The filter is instrument-specific, so it cannot alter GBPUSD, USDCHF, XAUUSD, AUDUSD, USDCAD, or USDJPY outcomes. Expected win-rate/PnL delta over this window: 0.0pp, 0 pips. The claimed +19.8pp improvement is entirely out-of-sample relative to the trades shown. OVER-TIME PROJECTION: Over 3–6 months, the filter would only affect future ETHUSD SHORT entries. The backtest shows n=59 — a small sample with high variance; a 19.8pp win-rate jump could easily be regime-specific (e.g., a trending ETHUSD period). Risk: the filter may overfit to recent ETHUSD volatility, and if the market shifts to range-bound or bullish, the short-only filter could suppress valid long entries and reduce total Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com