LAB #2285 PROMISING: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.5% to 33.1% (+1.6pp — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.5% to 33.1% (+1.6pp, n=1379) SAME-WINDOW EFFECT: Applying a pool-density filter (≥90) to the current live window would have excluded the XAUUSD SHORTs (rizzy5m) and likely the USDJPY SHORT (wkjudas) if their pool density was below threshold — but we lack per-trade density values. Of the 10 trades, 4 are losses (3 XAUUSD, 1 GBPUSD) and 5 are wins; if the filter removed 2–3 of the losing XAUUSD shorts, the window win rate would rise from 50% to ~60–70%, and PnL would improve by roughly +1.5R to +2.5R (assuming typical 1R loss per excluded trade). However, if any winning trades (e.g., EURJPY LONG) also had low density, the benefit shrinks — the backtest's +1.6pp is plausible but not guaranteed here. OVER-TIME PROJECTION: Over 3–6 months, a density≥90 filter should reduce low-conviction entries, lifting win rate from ~31.5% to ~33.1% as backtested, bu Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com