LAB #4082 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD LONG @ NY_OPEN with 5 conf — improves win rate from 32.5% to 76.2 — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD LONG @ NY_OPEN with 5 conf — improves win rate from 32.5% to 76.2% (+43.6pp, n=21) SAME-WINDOW EFFECT: Over the current live window, no XAUUSD LONG @ NY_OPEN trades exist — all XAUUSD activity is SHORT via rizzy5m, and none of the listed entries fall within NY_OPEN (09:30–10:30 ET) with 5 conf. Thus, this filter would have changed nothing in the current window — zero trades affected, zero PnL delta. The +43.6pp win-rate claim is based on n=21, which is statistically fragile and likely overfit to a specific regime; it does not translate to the current mixed-signal environment. OVER-TIME PROJECTION: Over 3–6 months, this filter could genuinely improve XAUUSD LONG precision if NY_OPEN liquidity and momentum alignment are real edge drivers — but the sample size is too small to separate signal from noise. Primary risk: the filter may simply be selecting for a narrow time window that coincides with 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: W7221749210
Cites:
Cited by:
Related to: