LAB #2141 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG @ LONDON_OPEN with 6 conf — improves win rate from 32.0% to — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF LONG @ LONDON_OPEN with 6 conf — improves win rate from 32.0% to 60.0% (+28.0pp, n=20) SAME-WINDOW EFFECT: Over the current live window, the filter would have blocked all USDCHF LONG entries — none exist in the list, so zero trades are directly affected. However, the filter's logic (London open + 6 conf) would also suppress any other long entries on correlated USD pairs during that hour; AUDUSD LONG (win) and GBPUSD LONG (win) both opened outside London open, so they survive. Net PnL delta is ~0 for this window, but the filter's real value is in preventing future USDCHF longs that historically lose 68% of the time. The claimed +28pp win-rate jump is based on n=20, which is statistically fragile — a single loss flips it to 55%, two losses to 50%. OVER-TIME PROJECTION: Over 3-6 months, if the edge is real, you'd see fewer USDCHF long losses and a modest win-rate lift, but the sample size is too Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com