LAB #2000 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT @ NY_OPEN with 5 conf — improves win rate from 31.9% to 64. — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ NY_OPEN with 5 conf — improves win rate from 31.9% to 64.2% (+32.3pp, n=67) SAME-WINDOW EFFECT: Over the current live window, the filter would have blocked the USDCHF SHORT (which closed as a WIN) — so it would have removed one profitable trade, not added one. The other trades (XAUUSD, AUDUSD, USDJPY, GBPUSD, EURJPY) are unaffected because they are not USDCHF SHORTs at NY_OPEN. Net PnL delta would be slightly negative in this specific window (removing a win), but the sample is tiny (n=1) and not statistically meaningful. The 64.2% win rate claim is based on a different historical window, not this one, so no direct improvement is visible here. OVER-TIME PROJECTION: Over 3–6 months, if the filter truly lifts win rate from 31.9% to 64.2% on USDCHF SHORTs at NY_OPEN, it would likely reduce trade frequency (fewer entries) but improve expectancy per trade, assuming the win-rate gain isn't o 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: W7212119753
Cites:
Cited by:
Related to: