LAB #4170 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG — improves win rate from 32.6% to 39.3% (+6.7pp, n=145) — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF LONG — improves win rate from 32.6% to 39.3% (+6.7pp, n=145) SAME-WINDOW EFFECT: Over the current live window, applying the USDCHF LONG filter would have had zero direct impact — none of the 10 listed trades are USDCHF LONG entries. The claimed +6.7pp win-rate improvement (n=145) is derived from a backtest subset that does not overlap with the live trades shown, so no PnL delta would materialize here. The filter would only alter future trade selection, not retroactively change any of these outcomes. Thus, within this specific window, the adjustment is inert. OVER-TIME PROJECTION: Over 3–6 months, the filter could plausibly raise overall win rate if USDCHF LONG trades are indeed a persistent weak spot — but the sample (n=145) is modest, and the +6.7pp gain may be regime-dependent (e.g., USD strength cycles). Risks include overfitting to a single pair-direction during a favorable period, and th 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: W7222891307
Cites:
Cited by:
Related to: