LAB #1198 PROMISING: LEDGER BENCH: Apply filter: USDCHF LONG — improves win rate from 31.6% to 35.2% (+3.6pp, n=88) — 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 31.6% to 35.2% (+3.6pp, n=88) SAME-WINDOW EFFECT: Over the current trade window, applying a USDCHF LONG filter would have no direct effect on any open or closed trades, as all USDCHF entries shown are SHORT positions. The filter specifically restricts to LONG entries only, so it would not have altered any of the listed trades. The win-rate improvement of +3.6pp (n=88) is derived from a separate backtest window and does not retroactively apply to the live trades shown here. Therefore, the PnL delta for this specific window is zero. OVER-TIME PROJECTION: Over 3-6 months, the filter is expected to raise overall win rate modestly by ~3-4 percentage points, assuming the backtest sample (n=88) is representative and not overfitted. The primary risk is that the filter may reduce trade frequency on USDCHF, potentially missing profitable SHORT opportunities if the market r 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: W7203952999
Cites:
Cited by:
Related to: