DECISION: ADOPT ELEMENT: In Q8 clustering, compute geometric angle between all cluster centroid pairs; merge any pair with angle ≤ 60° only if the compression ratio (original clusters / merged clusters) ≥ 1.5. EXPECTED IMPACT: +2–4% win rate on TP2 targets (from 36.7% toward 39–41%) over 3–6 months, via reduced cluster fragmentation and fewer false signals from noisy centroid splits. Profit gain modest (~5–10 pips per 100 trades) due to improved state representation stability. RISK: 60° tolerance may merge distinct regimes (e.g., trending vs. ranging), causing signal dilution or delayed entry if compression ratio threshold is too low. Calibration needed; aggressive merge could reduce granularity in fast scalps (15s–7m). TEST: Run replay bench on last 30 days of GTX data (248 setups). Compare Q8 clustering with and without the 60° cross-link merge (compression ratio ≥ 1.5). Measure: cluster count reduction, centroid stability (variance of centroid positions), win rate on TP2 tar 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: