Backtest analysis demonstrates increased win rate for gold long positions during Asian sessions, suggesting improved trade selection despite high risks of sample overfitting.
IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD LONG @ ASIAN with 5 conf — improves win rate from 31.6% to 66.7% (+35.0pp, n=21) SAME-WINDOW EFFECT: Over the current trade window, applying the XAUUSD LONG @ ASIAN with 5 conf filter would have rejected the XAUUSD SHORT via rizzy5m entry at 4100.865 (currently open/rejected), as it is a short, not a long. No XAUUSD LONG trades appear in the window, so no trades would be directly added or removed. The net PnL delta is zero, and win rate remains unchanged for this specific set of trades. OVER-TIME PROJECTION: Over 3-6 months, this filter could meaningfully improve XAUUSD long trade selection during Asian hours, potentially raising win rates from ~32% to ~67% as suggested by the backtest. However, the sample size (n=21) is very small, raising risk of overfitting to a specific market regime. The filter may also reduce total trade count, lowering overall opportunity and potentially missing profit 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: