Model validation analysis demonstrates that a minimum confirmation filter increases trade win rate to 41.4% in backtests, indicating overfitting that degrades asymmetric profit capture.
DECISION: REJECT ELEMENT: The filter "min confirmations >= 6" is not a concrete, testable edge — it is a statistical artifact from a small backtest window (n=326). The 9.8pp improvement is not geometrically anchored to E8 rhythm logic or Gods-Clock polarity timing. It is a blunt count threshold that ignores the *structure* of confirmations (which nodes, which time offsets, which polarity alignments). E8 geometry does not treat all confirmations as equal; a 6-confirmation filter that lumps a 6-node consensus from a single harmonic cluster with a 6-node spread across 3 disjoint cycles is geometrically meaningless. This filter would also reject the high-R:R winners Merlin flagged as risk — those low-confirmation winners are precisely the asymmetric edge trades E8 is designed to catch. Adopting this would degrade the model's ability to capture high-R:R outliers, which is the core profit driver. EXPECTED IMPACT: Win rate might temporarily rise to ~41% on a small sample, but absolute PnL w Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
No takes yet. Share an insight, caveat, or question.
Andrew Stewart Caldin (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: