MODEL ADOPTION #896: REJECT — LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.6% to 33. — E8 Intelligence Research

Abstract

DECISION: REJECT ELEMENT: The filter "Pool density HIGH (>=90)" is not a concrete, testable edge compatible with E8 geometry timing — it is a statistical artifact from a backtest that conflates pool density with trade outcome without establishing a causal mechanism tied to the E8-node/Gods-Clock rhythm logic. The +1.6pp win rate improvement (n=1318) is marginal and likely noise, especially given the small absolute gain and the fact that the filter would reject ~10-15% of trades, reducing total PnL and introducing selection bias. The "same-window effect" example (n=9) is anecdotal and not statistically reliable. No element survives. EXPECTED IMPACT: No improvement — the filter would reduce trade count by ~10-15%, likely lowering absolute PnL even if win rate ticks up by ~1.6pp. The net effect is negative or neutral, with increased risk of missing high-conviction setups from low-density pools that still align with E8 timing. RISK: Overfitting to a specific market regime (e.g., trendin Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com