LAB #4057 NEUTRAL: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 32.5% to 34.0% (+1.5pp — E8 Intelligence Research

Abstract

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=1817) SAME-WINDOW EFFECT: Applying a pool-density filter (≥90) would have excluded the majority of the listed live trades, as most entries (wkjudas and rizzy5m/7m) appear to originate from lower-density pools. Specifically, the two rizzy5m losses (NZDUSD, XAUUSD) and the wkjudas GBPUSD loss would likely have been filtered out, while the two wins (GBPUSD rizzy5m, EURUSD rizzy7m) might also be excluded if their pool density was below threshold. Net effect on this small sample is ambiguous—removing both wins and losses could leave PnL roughly flat, but the +1.5pp win-rate improvement from backtest suggests a modest positive shift if the filter selectively removes low-probability entries. Expected PnL delta here is near zero to slightly positive, but not statistically meaningful at n=10. OVER-TIME PROJECTION: Over 3–6 months, a Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com