LAB #2241 NEUTRAL: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.7% to 33.4% (+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 31.7% to 33.4% (+1.6pp, n=1370) SAME-WINDOW EFFECT: Applying the pool density ≥90 filter would have excluded the XAUUSD SHORTs (rizzy5m entries at 4048.74 and 4051.79) and likely the EURJPY SHORT (rizzy5m at 184.144) if their pool density fell below threshold — all three were losses. That removes 3 losing trades from 10, leaving 7 trades with 4 wins and 3 losses (57% win rate vs. current 40%). PnL delta is positive but modest: you avoid three full losses (likely −2R to −3R total) while keeping all winners, so net gain ≈ +2.5R over this window. However, the filter would not have saved the GBPUSD SHORT loss (rizzy5m, 1.34508) if that pool density was high — so it's not a universal loss filter. OVER-TIME PROJECTION: Over 3–6 months, a +1.6pp win-rate improvement on n=1370 is statistically weak (p≈0.08–0.12) and likely overfit to a specific regime. The f Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com