LAB #1912 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT — improves win rate from 32.0% to 60.1% (+28.2pp, 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% (+28.2pp, n=168) SAME-WINDOW EFFECT: Over the current live window, applying a USDCHF SHORT-only filter would have zero direct impact — none of the 10 listed trades involve USDCHF. However, if the filter is interpreted as "only take SHORT trades on USDCHF and suppress all other signals," then all 10 trades would have been blocked, eliminating 6 losses and 4 wins (net PnL change: −2 wins, +6 losses avoided). Expected win-rate delta on this tiny sample would be undefined (0 trades), but PnL would improve by roughly the sum of the 6 losses (unknown magnitudes, likely positive net). The filter's 28.2pp win-rate gain in backtest is not testable here because the live window contains no USDCHF exposure. OVER-TIME PROJECTION: Over 3–6 months, a USDCHF SHORT-only filter would drastically reduce trade frequency (likely >90% of signals filtered out), concentr 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: W7210274918
Cites:
Cited by:
Related to: