LAB #4070 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT @ ASIAN with 5 conf — improves win rate from 32.6% to 63.2% — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ ASIAN with 5 conf — improves win rate from 32.6% to 63.2% (+30.6pp, n=19) SAME-WINDOW EFFECT: Over the current live window, this filter would have blocked the USDCHF SHORT trades only if they existed — none of the listed trades are USDCHF, so zero direct impact on the current book. However, the filter's logic (SHORT + ASIAN session + 5 conf) is a subset of a broader "avoid USDCHF longs during Asia" rule; if applied globally, it would not have touched GBPUSD, USDJPY, NZDUSD, AUDUSD, or XAUUSD trades. The only indirect effect is opportunity cost: if the engine had been forced to skip USDCHF SHORTs, it might have reallocated capital to other pairs, but with n=19 the edge is statistically fragile. Expected PnL delta over this window: ~0. OVER-TIME PROJECTION: Over 3-6 months, a +30.6pp win-rate jump from a filter with n=19 is almost certainly overfit to a specific market regime (likely a 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: W7221809523
Cites:
Cited by:
Related to: