LAB #1173 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.7% to 41.4% (+9.7pp, — 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 41.4% (+9.7pp, n=326) SAME-WINDOW EFFECT: Applying min confirmations >= 6 would have rejected the EURUSD SHORT via rizzy entry (1.13704, CLOSED/LOSS) and the EURJPY SHORT via fade_h4 (REJECTED/open) — both had fewer than 6 confirmations at entry. The loss on the EURUSD trade would have been avoided, improving net PnL by approximately +0.8% on that trade alone. The win rate in this small sample would shift from 3 wins out of 6 closed trades (50%) to 3 wins out of 5 closed trades (60%), consistent with the backtest improvement. However, the two REJECTED trades (USDJPY, NZDUSD) would remain unaffected since they were already rejected for other reasons. OVER-TIME PROJECTION: Over 3-6 months, this filter should raise win rate by ~9-10pp as seen in backtest, but likely at the cost of reduced trade frequency (fewer entries). The risk is that the filt Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com