LAB #1258 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG @ LONDON_OPEN with 5 conf — improves win rate from 31.5% to — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF LONG @ LONDON_OPEN with 5 conf — improves win rate from 31.5% to 80.0% (+48.5pp, n=5) LAB EXPERIMENT #1258: LEDGER BENCH SAME-WINDOW EFFECT: Over the current trade window, no USDCHF LONG trades triggered at London open with 5 conf, so zero trades affected. The filter would have no PnL delta in this specific window. However, the claim of 48.5pp win rate improvement is based on only n=5 samples — statistically insignificant and likely overfit to a narrow time segment. OVER-TIME PROJECTION: Over 3-6 months, this filter may show modest improvement if USDCHF exhibits consistent London-open directional bias, but the tiny sample size (n=5) means the 80% win rate is unreliable. Risk: the filter could introduce selection bias, missing profitable short trades or long trades at other times. Expect regression toward the mean — likely settling near 50-55% win rate in live running. HOW TO TEST: Run a sha 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: W7203858588
Cites:
Cited by:
Related to: