LAB #3861 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 32.5% to 34.0% (+1.5pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 5 — improves win rate from 32.5% to 34.0% (+1.5pp, n=1803) SAME-WINDOW EFFECT: Applying a minimum 5-confirmation filter would have rejected the AUDUSD SHORT (currently open/rejected) and likely the NZDUSD LONG (wkjudas, open) if confirmations were below threshold at entry. Among the 10 live trades, the filter would have removed at least 2 losers (NZDUSD SHORT, XAUUSD SHORT) if their confirmations were <5, but would also have removed the GBPUSD SHORT WIN if it had <5 confirmations — net effect on this tiny sample is ambiguous. Given the backtest delta (+1.5pp win rate), the expected PnL change here is roughly neutral to slightly positive, but the sample is too small to confirm. OVER-TIME PROJECTION: Over 3–6 months, a +1.5pp win-rate improvement with n=1803 suggests a modest but real edge, likely from filtering out low-conviction entries that fail more often. However, this filter Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com