LAB #1295 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=1330) SAME-WINDOW EFFECT: Over the current live trade window, applying a minimum of 5 confirmations would have rejected the EURUSD SHORT via rizzy5m (entry 1.13594, CLOSED) and the USDJPY SHORT via wkjudas (entry 163.796, REJECTED) — both likely had fewer than 5 confirmations at entry. This filter would have prevented the EURUSD loss and the USDJPY rejection, potentially improving the window's win rate by ~1-2pp and reducing drawdown. However, it would not have affected the GBPUSD LONG (still open) or the other trades, so the net PnL delta is modest but positive. OVER-TIME PROJECTION: Over 3-6 months, this filter should sustain a win-rate improvement of ~1.5pp, as the backtest suggests, by eliminating low-conviction entries that often fail. The risk is that it may also filter out some high-reward trades that trigger early with Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com