MODEL ADOPTION #1015: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.6% to 33.2% — 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 heuristic derived from a backtest that does not isolate the *cause* of the win-rate improvement. The +1.6pp gain may be a spurious correlation with market regime, not a causal rule. E8-node/Gods-Clock rhythm logic already defines confirmation thresholds based on fractal alignment, not arbitrary integer counts. Adding this filter would override the native timing logic, likely degrading the model's ability to catch early entries that are geometrically valid but numerically low in confirmations. EXPECTED IMPACT: Negligible or negative. The backtest's +1.6pp win rate is small and may not replicate live due to selection bias (the 1328 trades are not independent of the filter's own effect on trade selection). The filter would reduce trade count by ~20-30%, and the rejected trades may have higher average R-multiples, lowering total profit eve Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com