LAB #3748 HARMFUL: LEDGER BENCH: Apply filter: GBPUSD LONG @ LONDON_OPEN with 6 conf — improves win rate from 32.3% to — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: GBPUSD LONG @ LONDON_OPEN with 6 conf — improves win rate from 32.3% to 87.5% (+55.2pp, n=8) SAME-WINDOW EFFECT: Over the current live window, the filter would have blocked the two GBPUSD SHORT trades (rizzy5m and rizzy7m) since it only allows LONG at London open with 6 conf. The rizzy5m GBPUSD SHORT was a WIN, so blocking it would have removed a profitable trade; the rizzy7m GBPUSD SHORT is still open, so its outcome is unknown. No GBPUSD LONG trades exist in the window, so the filter would have added zero new trades. Net effect: win rate would drop (removing one win from a small sample) and PnL would likely decrease, not improve. OVER-TIME PROJECTION: The claimed +55.2pp improvement is based on n=8, which is statistically meaningless — the 95% confidence interval spans roughly ±30pp, so the true effect could easily be negative. Over 3-6 months, this filter would drastically reduce trade frequency Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com