LAB #2347 NEUTRAL: LEDGER BENCH: Apply filter: Phase distance FAR (>10deg) — improves win rate from 31.2% to 31.5% (+0. — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Phase distance FAR (>10deg) — improves win rate from 31.2% to 31.5% (+0.3pp, n=688) SAME-WINDOW EFFECT: Applying the FAR (>10deg) filter to the 10 live trades above would have removed trades where phase distance was ≤10deg. Based on the backtest delta (+0.3pp), this filter would have likely excluded 1–2 of the 4 losses (e.g., the USDJPY SHORT or GBPUSD SHORT) while keeping most winners, yielding a net win-rate improvement from 50% (5/10) to roughly 60–67% (6–7/10) in this small sample. PnL delta is marginal but positive, roughly +0.5R to +1.0R, assuming excluded losers were typical −1R and no excluded winner was large. However, with n=10, the effect is statistically indistinguishable from noise. OVER-TIME PROJECTION: Over 3–6 months, a +0.3pp win-rate gain on ~688 trades is real but tiny — roughly 2 extra wins per 100 trades. The risk is overfitting to a narrow phase-distance threshold; if the marke Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com