LAB #2172 NEUTRAL: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.9% to 33.5% (+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 31.9% to 33.5% (+1.6pp, n=1360) SAME-WINDOW EFFECT: Applying the pool-density filter (≥90) to the current 10-trade window would have excluded trades where pool density was below threshold. Based on the backtest delta (+1.6pp win rate), roughly 1-2 of the 10 trades would likely be filtered out — most plausibly the XAUUSD shorts (which show 3 losses out of 4) or the GBPUSD short loss. If those low-density losers were removed, the window's win rate would improve from 5/10 to ~5/8 or 6/8, a meaningful PnL gain of roughly +1.5R to +2.5R. However, the one open trade (USDJPY SHORT) and the two wins via rizzy7m and sqz may also be affected, so the net effect is positive but not transformative at this sample size. OVER-TIME PROJECTION: Over 3-6 months, a +1.6pp win-rate improvement on a base of ~31.9% is statistically marginal (n=1360 gives a standard error o Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com