Quantitative model evaluation demonstrates net expectancy loss from Wyckoff spring filters, indicating trade volume reductions outweigh win-rate improvements.
DECISION: REJECT ELEMENT: No single rule survives hostile scrutiny. The spring/upthrust filter is a *contextual* overlay, not a timing edge. E8 geometry already defines entry timing; adding a Wyckoff range filter would require redefining what a "range" is on 15s–7m charts, and your own projection admits it would reject 30–40% of trades while only improving win-rate by 5–8% — that's a net expectancy loss unless the filter is *perfect*, which it cannot be given the subjective "false break" definition. EXPECTED IMPACT: If adopted, win-rate might rise from ~50% to ~55–58% on surviving trades, but trade count drops by a third. Total profit likely *decreases* because you lose the high-frequency compounding that the live model relies on. The two losing XAUUSD shorts you cited were not "springs" — they were trend continuation failures. A filter that rejects trend-continuation losses is just a trend-following rule in disguise, and you already have that via rizzy5m/wkjudas. No new edge. 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: