LAB #4385 PROMISING: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.6% to 33.1% (+1.4pp — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.6% to 33.1% (+1.4pp, n=1903) SAME-WINDOW EFFECT: Applying the pool density ≥90 filter would have excluded the three wkjudas trades (GBPUSD LONG, USDJPY SHORT, NZDUSD SHORT) — all three were losses. That would have removed 3 losses from the 10-trade window, shifting the record from 4W/3L/3open to 4W/0L/3open among closed trades. Win rate among closed trades improves from 57% to 100%, and PnL delta is strongly positive (avoiding 3 full losses). However, the two rizzy7m trades (USDCHF LONG win, AUDUSD SHORT loss) and the rizzy5m trades remain unaffected, so the filter's benefit here is concentrated on wkjudas signals only. OVER-TIME PROJECTION: Over 3–6 months, a +1.4pp win-rate gain from a density filter is plausible but modest — it likely reduces trade count by 10–20% while cutting low-conviction losers. Risk: the filter may be overfit to a specifi Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com