LAB #4031 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=1816) SAME-WINDOW EFFECT: Applying a minimum-5-confirmation filter would have removed the two earliest rizzy5m entries (AUDUSD 08-27, NZDUSD 08-27) and the XAUUSD 08-27 short — all three were losses or rejected. It would also have excluded the EURJPY long (08-26, loss) and the EURUSD long (08-25, win), netting a wash on wins/losses. The net effect on this small window is roughly neutral to slightly positive, as you remove 4 losses and 1 win, but the remaining sample is too small to confirm the +1.5pp backtest edge. The live window shows no clear confirmation-dependent pattern — losses appear at both high and low confirmation counts. OVER-TIME PROJECTION: Over 3–6 months, a +1.5pp win-rate gain from a confirmation filter is plausible but likely comes at a cost of reduced trade frequency (fewer entries, especially in fast-moving Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com