LAB #1969 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD LONG @ ASIAN with 5 conf — improves win rate from 32.0% to 66.7% — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD LONG @ ASIAN with 5 conf — improves win rate from 32.0% to 66.7% (+34.6pp, n=21) SAME-WINDOW EFFECT: Over the live window, the filter would have blocked the three XAUUSD SHORTs (all losses) and would have allowed only XAUUSD LONGs with 5 conf — but no such LONG exists in the window, so net effect is zero trades added. However, it would have removed 3 losing XAUUSD SHORTs from the sample, shifting the visible win rate from roughly 4/8 (50%) to 4/5 (80%) on remaining trades — but that's a selection artifact, not a real PnL gain. The actual PnL delta is +0 (no new longs triggered), and the filter only masks losses by excluding them from the denominator. The claimed +34.6pp improvement is likely a backtest overfit to a tiny n=21, not a live edge. OVER-TIME PROJECTION: Over 3–6 months, this filter would reduce XAUUSD trade frequency by ~50–70% (only longs with 5 conf), which could cut total trades 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: W7212007096
Cites:
Cited by:
Related to: