Answers are grounded in this paper and cite their sources.
IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD LONG @ ASIAN with 5 conf — improves win rate from 31.0% to 66.7% (+35.6pp, n=21) SAME-WINDOW EFFECT: Over the live window shown, the filter would have blocked the XAUUSD SHORT entries on 2026-08-04 and 2026-07-31 (both losses), while allowing the XAUUSD LONG on 2026-08-06 (win). That removes 2 losses and keeps 1 win, flipping the window's XAUUSD record from 1W/2L to 1W/0L. Net PnL delta is positive but small (roughly +2R), and the overall trade count drops by 2, which slightly reduces sample size for other signals. OVER-TIME PROJECTION: Over 3–6 months, this filter would likely improve XAUUSD-specific win rate if the Asian-session LONG edge persists, but the n=21 backtest is dangerously small — a single loss swings the result by ~5pp. The main risk is overfitting to a specific session/conf combination that may not generalize across gold's regime shifts (trending vs. ranging). Also, blocking S 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 8 closely related papers on similar clinical questions. Consider them for comparative context: