LAB #4106 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT — improves win rate from 32.6% to 52.6% (+20.0pp, n=274) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT — improves win rate from 32.6% to 52.6% (+20.0pp, n=274) SAME-WINDOW EFFECT: Applying a USDCHF SHORT-only filter would have zero effect on the current live window — none of the 10 listed trades are USDCHF. The backtested +20.0pp win-rate improvement (n=274) is not represented here, so no PnL delta would occur in this specific sample. This is a classic case of a filter that may be statistically strong in aggregate but irrelevant to the current active trade set — it neither helps nor hurts the live book right now. OVER-TIME PROJECTION: Over 3–6 months, a USDCHF SHORT filter could plausibly lift overall win rate if USDCHF short setups are a meaningful fraction of total signals and the backtest is not overfit. However, the +20pp jump on n=274 is suspiciously large — likely driven by a specific regime (e.g., USD strength cycle) that may not persist. Risk: the filter could silently exclude pr Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com