LAB #1174 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.7% to 33.2% (+1.6pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 5 — improves win rate from 31.7% to 33.2% (+1.6pp, n=1321) SAME-WINDOW EFFECT: Over the current live trade window, applying a min confirmations >= 5 filter would have rejected the GBPUSD LONG (wkjudas, entry=1.32842) and the NZDUSD LONG (wkjudas, entry=0.57702) since both show only 1 confirmation signal. The EURUSD SHORT (rizzy5m, entry=1.13594) and USDJPY SHORT (wkjudas, entry=163.796) would also be rejected. This would reduce total trade count by 4, likely eliminating 2-3 low-confidence losers from the window, but also potentially removing the GBPUSD LONG if it becomes a winner. Expected win-rate improvement of ~1-2pp in this small sample, with PnL delta slightly positive due to avoided losses. OVER-TIME PROJECTION: Over 3-6 months, the filter should sustain a win-rate improvement of 1-2pp as seen in the backtest, reducing noise from early-entry signals that fade. However, the Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com