LAB #327 PROMISING: LEDGER BENCH: Apply filter: Phase distance TIGHT (<=2deg) — improves win rate from 32.4% to 36.8% (+ — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Phase distance TIGHT (<=2deg) — improves win rate from 32.4% to 36.8% (+4.4pp, n=370) SAME-WINDOW EFFECT: Applying phase distance TIGHT (<=2deg) to the current live window would have rejected the two wkjudas GBPUSD trades (both losses) and the wkjudas NZDUSD loss, while retaining the rizzy5m USDCHF win and the rizzy7m EURUSD win. The two rizzy5m AUDUSD rejects and the fade_h4 EURJPY reject would remain unchanged. This would have shifted the window from 3 wins, 4 losses, 3 rejects to 2 wins, 1 loss, 7 rejects — a win-rate improvement from 42.9% to 66.7% on closed trades, but with a significant reduction in total trade count and likely lower absolute PnL due to missed opportunities. OVER-TIME PROJECTION: Over 3-6 months, the +4.4pp win-rate gain from the backtest (n=370) suggests a modest but reliable improvement in signal quality, likely reducing drawdowns and increasing Sharpe ratio. However, the fi Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com