LAB #4168 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD LONG — improves win rate from 32.6% to 55.4% (+22.8pp, n=83) — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD LONG — improves win rate from 32.6% to 55.4% (+22.8pp, n=83) SAME-WINDOW EFFECT: Over the current live window, no XAUUSD trades appear in the list, so this filter would have changed nothing in the actual executed trades shown. The only XAUUSD trade listed is a SHORT (via rizzy5m, entry 4598.79, closed as LOSS) — your filter is for LONG only, so it would not have blocked or altered that losing short. Therefore, the claimed +22.8pp win-rate improvement is not observable in this window; the live PnL delta is zero. The filter's benefit, if real, must come from a different historical subset not represented here. OVER-TIME PROJECTION: Over 3–6 months, restricting to XAUUSD LONG would drastically reduce trade frequency — XAUUSD longs are a narrow slice of your multi-pair engine. The win-rate jump from 32.6% to 55.4% on n=83 is statistically fragile (standard error ~5.5pp, so the true effect could be Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Author: Caldin, Andrew Stewart
Language: English
Subfield: Finance
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7222895552
Cites:
Cited by:
Related to: