LAB #1867 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT — improves win rate from 32.0% to 60.1% (+28.1pp, n=168) — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT — improves win rate from 32.0% to 60.1% (+28.1pp, n=168) SAME-WINDOW EFFECT: Applying the USDCHF SHORT filter would have zero effect on the current live window, as none of the 10 listed trades involve USDCHF. The filter is instrument- and direction-specific, so it cannot alter outcomes for GBPUSD, XAUUSD, EURJPY, AUDUSD, or EURUSD trades. Therefore, the claimed +28.1pp win-rate improvement is untestable against this window — it neither helps nor hurts current positions. The only potential indirect effect is if the filter changes model routing logic (e.g., reallocating capital), but as stated, it is purely a trade-selection filter with no overlap here. OVER-TIME PROJECTION: Over 3–6 months, a USDCHF SHORT filter could plausibly improve overall win rate if the backtest is not curve-fit, but the sample (n=168) is small and the +28.1pp jump is suspiciously large for a single filter — likely 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: W7208837220
Cites:
Cited by:
Related to: