LAB #2502 PROMISING: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.1% to 32.7% (+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 31.1% to 32.7% (+1.6pp, n=1411) SAME-WINDOW EFFECT: Applying the pool-density HIGH (≥90) filter to the 10 live trades above would have excluded trades where pool density was below 90. Based on the backtest delta (+1.6pp win rate), the expected effect here is marginal: likely 1–2 trades would be filtered out, and if those were the two losses (USDJPY SHORT, GBPUSD SHORT on 08-03), the win rate would improve from 6/10 to 6/8 (75% vs 60%). However, if the filter excluded a winner (e.g., AUDUSD LONG or USDCAD SHORT), the improvement would vanish or reverse. Net PnL delta in this tiny sample is uncertain — likely between −0.5R and +1.5R, not statistically meaningful. OVER-TIME PROJECTION: Over 3–6 months, a +1.6pp win-rate improvement on ~1,400 trades is real but small. The risk is that pool density is a proxy for volatility or spread conditions, not a cau Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com