MODEL ADOPTION #1277: REJECT — LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.7% to 33. — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: DECISION: REJECT ELEMENT: The filter "pool density >= 90" is not a concrete, testable edge compatible with E8 geometry timing. It is a statistical artifact from a backtest window (n=1330) with no demonstrated causal link to the rhythm logic of E8-node/Gods-Clock or the FADE polarity edge. The 1.6pp win-rate improvement is marginal and likely overfit to a specific market regime. The filter rejects trades based on a non-geometric, non-temporal condition, which violates the core premise of E8: timing and polarity are primary, density is secondary at best. EXPECTED IMPACT: Negligible to negative. Win-rate may tick up slightly (0–1pp) but trade count drops significantly, reducing total net profit. The filter cuts high-reward, low-density setups that may be the source of outsized gains. Over 3–6 months, the filter's selectivity will likely decay as pool density distributions shift, leading to worse performance than the unfiltered baseline. RISK: Overfitting to a specific backtest window. 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: W7203870198
Cites:
Cited by:
Related to: