MODEL ADOPTION #2049: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.0% to 42.2% — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: DECISION: REJECT ELEMENT: No single rule survives — the 6-confirmation filter is a statistical artifact, not an E8-geometry edge. EXPECTED IMPACT: Win rate would rise ~10pp in backtest, but net profit likely falls due to 20-30% fewer trades, including cutting early reversals (e.g., EURJPY win). The filter correlates with time-of-day/volatility, not rhythm phase — it does not align with Gods-Clock polarity timing. RISK: Overfits to recent XAUUSD chop; in trending regimes, it will miss high-probability fade entries at exact E8 nodes where confirmations are naturally low (fast momentum). Also, reducing trade count increases variance per trade, degrading the model's statistical stability. TEST: Before any re-adoption, run a 90-day replay-bench on all 10 pairs with three parallel ledgers (current, ≥6 confirmations, ≥4 confirmations). Require ≥500 filtered and ≥500 unfiltered signals per pair. Pass condition: filtered set must show ≥45% win rate AND ≥+0.3R average per trade AND no in 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: W7212238113
Cites:
Cited by:
Related to: