LAB #2632 PROMISING: LEDGER BENCH: Apply filter: Phase distance TIGHT (<=2deg) — improves win rate from 31.0% to 35.4% (+ — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Phase distance TIGHT (<=2deg) — improves win rate from 31.0% to 35.4% (+4.4pp, n=441) SAME-WINDOW EFFECT: Applying the phase-distance TIGHT (≤2°) filter would have removed the three LOSS trades (XAUUSD SHORT 4048.74, USDJPY SHORT 157.883, GBPUSD SHORT 1.34508) and likely the REJECTED USDCHF trade, while keeping all five WIN trades intact. That shifts the live window from 5W/3L (62.5% win rate) to 5W/0L (100% win rate) — a dramatic improvement, but the sample is tiny (n=8). PnL delta would be strongly positive, roughly +3R to +4R, but this is heavily influenced by the fact that the filter happens to catch all losers in this specific window — a classic overfit risk. OVER-TIME PROJECTION: Over 3–6 months, the filter should reduce false entries by cutting trades where phase alignment is weak, which historically correlates with lower win probability. However, the +4.4pp gain from n=441 backtest is modest Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com