MODEL ADOPTION #3822: REJECT — LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 32.5% to 34. — E8 Intelligence Research
Abstract
DECISION: REJECT ELEMENT: No element survives — the pool-density ≥90 filter is a statistical artifact, not an E8-geometry-compatible edge. EXPECTED IMPACT: The +1.5pp backtest gain (n=1800) is within noise for a 32.5%→34.0% shift (σ≈1.1pp). Merlin's own live-window projection shows only +8.6pp on 7 trades (n=7, meaningless), and PnL delta is ~+0.5R — not enough to justify added complexity. The filter does not align with E8 rhythm logic (Gods-Clock timing, FADE polarity); it's a liquidity proxy that will misfire across instruments (EURJPY/XAUUSD density distributions differ). RISK: Global ≥90 cutoff over-filters metals and JPY crosses, excluding high-conviction E8 entries during legitimate low-density but high-timing setups. Adds post-entry latency if density is computed after signal generation, degrading the FADE edge. Overfits to a 30-day window; regime shift to thinner pools would kill the filter's benefit while still excluding winners. TEST: No test can save this — even if a Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
