MODEL ADOPTION #1110: REJECT — LEDGER BENCH: Apply filter: USDCHF SHORT — improves win rate from 31.7% to 61.2% (+29.5pp, — E8 Intelligence Research

Abstract

DECISION: REJECT ELEMENT: The filter "block all USDCHF SHORT trades" is a blunt instrument that contradicts E8 geometry timing, which relies on polarity edges, not static pair-direction bans. The backtest (n=165) is too small and likely period-fitted; the same-window effect already shows it would have removed a winning trade. No concrete, testable edge compatible with E8 rhythm logic is provided. EXPECTED IMPACT: Win rate may rise on USDCHF SHORTs, but total PnL likely drops due to missed trend-following wins and reduced trade frequency. The 30pp win-rate gain is not credible without walk-forward validation across multiple CHF regimes. RISK: Overfitting to a narrow historical window; CHF strength regime shifts could invert the filter's effect; blocking trades based on pair-direction alone violates E8's polarity-agnostic timing. TEST: Before any reconsideration, run a walk-forward analysis on 2025–2026 data (minimum 500 trades) and a 90-day shadow-test on live swarm logging all Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com