LAB #1143 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.7% to 41.3% (+9.6pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 6 — improves win rate from 31.7% to 41.3% (+9.6pp, n=334) SAME-WINDOW EFFECT: Over the current live trade window, applying a min confirmations >= 6 filter would have rejected the EURUSD SHORT via rizzy5m (entry 1.13594, currently CLOSED but status unclear) and likely the NZDUSD LONG via wkjudas (entry 0.57702, REJECTED). The two confirmed wins (USDCAD LONG, GBPUSD SHORT) both came from rizzy7m signals, which typically generate higher confirmation counts, so they would likely survive the filter. The net effect would be a reduction in total trades from 10 to roughly 6-7, with the win rate improving from the observed ~40% (4 wins out of 10) to potentially 50-57% (4 wins out of 6-7), but total PnL might drop slightly due to fewer opportunities. OVER-TIME PROJECTION: Over 3-6 months, the +9.6pp win rate improvement from backtesting suggests this filter effectively kills low-convictio Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com