MODEL ADOPTION #4091: REJECT — LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 32.6% to 34. — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: DECISION: REJECT ELEMENT: No element survives — the pool density ≥90 filter is a statistical artifact, not a geometric edge. E8 timing is derived from Gods-Clock phase harmonics; pool density is a liquidity proxy that correlates with session windows, not with the model's entry rhythm. The +1.5pp gain is within noise for n=1825 (95% CI roughly ±2.3pp), and the live sample of 7 trades is anecdotal. The filter would reduce trade count by ~20-30%, capping absolute R even if win rate rises — this violates the "no more than 15% reduction in total R" test you set. No concrete mechanism ties density to E8's fade polarity timing; it's a meta-filter that could be replaced by a simple session filter (e.g., skip Asia) with less overfitting risk. EXPECTED IMPACT: If adopted, win rate might rise 0.5-1.0pp in the first month, but monthly R would drop 15-25% due to fewer trades, and the edge would decay as density regimes shift (e.g., during crypto volatility spikes or holiday liquidity). Net pro Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Author: Caldin, Andrew Stewart
Language: English
Subfield: Finance
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7222195891
Cites:
Cited by:
Related to: