MODEL ADOPTION #4177: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.6% to 38.3% — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: DECISION: REJECT ELEMENT: No single rule survives — the ≥6 confirmations filter is a statistical artifact, not an E8-geometry-compatible edge. EXPECTED IMPACT: Win-rate gain (+5.7pp) is real in backtest but profit-factor delta is unproven; likely reduces trade count by ~20-30%, cutting compounding and absolute PnL in live conditions. The filter does not align with Gods-Clock rhythm logic — it delays entries past optimal FADE polarity windows, degrading risk/reward on momentum breakouts. RISK: Overfits to recent low-volatility regimes; in trending markets, 6-confirmation lag causes late entries with wider stops, increasing max drawdown. Also removes occasional large winners (e.g., wkjudas GBPUSD LONG if it had been a winner), skewing the edge toward small wins and capped upside. TEST: Before any adoption, run a 90-day replay-bench on the live engine's historical tick data (E8-node timestamps) with two arms: (A) all signals, (B) ≥6 confirmations. Require ≥300 trades per arm, and 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: W7222869365
Cites:
Cited by:
Related to: