IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD LONG — improves win rate from 31.0% to 58.1% (+27.1pp, n=74) SAME-WINDOW EFFECT: Over the current live window, applying the XAUUSD LONG-only filter would have removed the three XAUUSD SHORT trades (all losses: 4048.74, 4051.79, and the 4270.17 LONG is kept as a win). That removes 3 losses and keeps 1 win, shifting the window from 5W/5L to 5W/2L — a win-rate jump from 50% to ~71% on remaining trades. PnL delta is strongly positive, as you eliminate three losing shorts while retaining all winning longs. However, note the filter also blocks any future XAUUSD SHORT that might win — the sample is tiny (n=74) and the live window only has 4 XAU trades total. OVER-TIME PROJECTION: Over 3–6 months, this filter could meaningfully improve overall win rate if XAUUSD continues to trend upward or range with bullish bias, as longs would dominate. The risk is regime shift: if gold enters a sustained downtren 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: