LAB #4981 NEUTRAL: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.7% to 33.2% (+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 31.7% to 33.2% (+1.5pp, n=1935) SAME-WINDOW EFFECT: The filter's claimed +1.5pp edge is a rounding-scale effect on a 31.7% base — it moves the needle from roughly 1-in-3 to 1-in-3. Over the 8-trade window shown, that's a statistical no-op: you cannot resolve a 1.5pp shift with n=8, and the filter would likely have removed some of the two winners (USDCHF LONG, USDCAD SHORT) if their pool density sat below 90, turning a 2W/3L/3-rejected book into 0W/3L. The three CLOSED/LOSS shorts (EURUSD, XAUUSD, AUDUSD) are exactly the kind of crowded, high-density setups the filter claims to avoid — so if density was genuinely HIGH on those entries, the filter did not fire and the +1.5pp is not describing this window at all. Net: no verifiable PnL delta, and a real risk of negative selection on the winners. OVER-TIME PROJECTION: A +1.5pp win-rate lift on n=1935 is Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com