MODEL ADOPTION #556: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 32.3% to 33.9% — E8 Intelligence Research

Abstract

DECISION: REJECT ELEMENT: The filter "min confirmations >= 5" is not a concrete, testable edge compatible with E8 geometry timing. It is a statistical band-aid derived from a backtest sample (n=1271) that conflates correlation with causation. The "confirmation count" is not a defined E8 rhythm parameter (e.g., Gods-Clock phase, FADE polarity, node alignment). Without a mechanistic link to the model's core logic, this filter is a black-box heuristic that will degrade in regime shifts. EXPECTED IMPACT: Win-rate improvement of +1.6pp is marginal and likely a product of overfitting to the specific 1271-trade sample. The projected 10-15% trade count reduction will cut total profit even if win rate rises slightly, because the rejected trades (low confirmations) may include high-RR breakouts that the E8 model is designed to catch. Net PnL impact is neutral to negative. RISK: The filter will systematically exclude early entries in fast-moving trends (e.g., breakout from a compressed Gods-Cl Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com