LAB #3884 PROMISING: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 32.5% to 34.0% (+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 32.5% to 34.0% (+1.5pp, n=1805) SAME-WINDOW EFFECT: Applying the pool-density ≥90 filter to the current live window would have excluded trades with low pool density. Among the 10 listed trades, the two losses from `rizzy5m` (NZDUSD and XAUUSD) and the `wkjudas` USDJPY loss likely fall below the threshold, removing 3 losses and 0 wins. That would shift the window from 2W/5L (28.6%) to 2W/2L (50%) — a +21pp improvement, but on a tiny sample. The AUDUSD open short and GBPUSD open would remain, so net PnL delta is positive but not statistically meaningful. OVER-TIME PROJECTION: Over 3–6 months, the +1.5pp win-rate gain (n=1805) is modest but real if the backtest is unbiased. However, pool density is a proxy for liquidity/volatility regime; filtering to HIGH density may reduce trade frequency (fewer setups) and could concentrate risk in fast-moving, high- Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com