LAB #4021 PROMISING: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 32.5% to 34.0% (+1.5pp — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Pool density HIGH (>=90) — improves win rate from 32.5% to 34.0% (+1.5pp, n=1816) SAME-WINDOW EFFECT: Over the current 10-trade window, the pool-density filter (≥90) would have affected only trades originating from signals with lower pool density. The two open wkjudas trades (GBPUSD LONG, USDJPY SHORT) and the closed NZDUSD LONG likely pass the filter if their pool density was high; the rizzy5m/7m trades are more likely to be filtered out, especially the three CLOSED/LOSS entries (NZDUSD, XAUUSD, EURJPY) and the REJECTED AUDUSD. Removing those low-density losers would have eliminated at least 3 losses and possibly the REJECTED trade, shifting the window from roughly 2W/3L/5open to 2W/0L/3open — a clear PnL improvement, though the sample is tiny and the open trades remain unresolved. OVER-TIME PROJECTION: Over 3–6 months, a +1.5pp win-rate gain from n=1816 suggests a modest but real edge, likely by c Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com