LAB #4134 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT — improves win rate from 32.6% to 52.3% (+19.8pp, n=277) — 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 32.6% to 52.3% (+19.8pp, n=277) SAME-WINDOW EFFECT: Over the current live window, applying a USDCHF SHORT-only filter would have excluded all trades listed, since none are USDCHF. Therefore, the immediate effect is zero trades affected and no PnL delta — the filter neither saves nor adds anything in this specific sample. The +19.8pp win-rate improvement is derived from a different historical backtest window (n=277) and does not translate to the current 10-trade live set. This highlights that the filter's benefit is conditional on market regime and pair-specific conditions, not a universal overlay. OVER-TIME PROJECTION: Over 3–6 months, restricting to USDCHF SHORT alone would drastically reduce trade frequency — likely from hundreds of setups to a handful per month, given the engine's current multi-pair scope. The win-rate gain may be real but could be offset by 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: W7222632856
Cites:
Cited by:
Related to: