Backtest analysis demonstrates improved win rate for Asian session XAUUSD long trades using a five-confirmation filter, suggesting potential gains despite small sample overfitting risks.
IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD LONG @ ASIAN with 5 conf — improves win rate from 31.5% to 66.7% (+35.1pp, n=21) SAME-WINDOW EFFECT: Over the current trade window, this filter would have blocked the XAUUSD SHORT via rizzy5m at 4100.865 (REJECTED/open) and any other XAUUSD LONG entries that lacked 5 conf during Asian hours. Since the only XAUUSD trade in the window was a rejected short, no live trades would have been directly altered. However, if the filter had been active, it might have prevented a theoretical XAUUSD LONG with 5 conf from being taken — but no such trade appears in the list, so PnL delta is effectively zero for this specific window. OVER-TIME PROJECTION: Over 3-6 months, applying this filter to XAUUSD LONG entries during Asian session with 5 conf could significantly improve win rate from ~31.5% to ~66.7%, based on the backtested n=21 sample. The risk is that the sample is small (21 trades) and may overfit to 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: