MODEL ADOPTION #1875: 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 element survives — the confirmation-count filter is a time-based proxy, not a geometric/rhythm edge. It does not align with E8-node/Gods-Clock timing; it merely removes low-confirmation entries, which in fast regimes are often the highest-quality fades (early entries = better R:R). The backtest +10.2pp is likely regime-luck, not structural. EXPECTED IMPACT: If adopted, win rate might rise ~3–5pp out-of-sample, but profit per trade would drop because you'd miss the best early fades (e.g., the rizzy5m XAUUSD shorts at 4051/4066 were low-confirmation but high-edge). Net expectancy likely flat or negative. RISK: Overfitting to a low-volatility window; in high-ATR regimes, confirmations lag price, so you'd enter late, get worse fills, and increase slippage. Also, filter interacts poorly with wkjudas/sqz — those already gate entries, so marginal benefit is near zero. TEST: Before any reconsideration, run a 90-day replay-bench on the live signal stream (no 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: W7210279577
Cites:
Cited by:
Related to: