LAB #3919 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.5% to 38.1% (+5.7pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 6 — improves win rate from 32.5% to 38.1% (+5.7pp, n=810) SAME-WINDOW EFFECT: Applying a minimum 6-confirmation filter would have eliminated the two `rizzy5m` entries (AUDUSD SHORT and NZDUSD SHORT) — both are low-timeframe, low-confidence signals. The NZDUSD SHORT was a loss; the AUDUSD SHORT is still open/rejected, so removing it avoids an unknown outcome. The remaining 8 trades (rizzy7m and wkjudas) would be unaffected, meaning the live window win rate would shift from 3 wins / 5 losses (37.5%) to 3 wins / 4 losses (42.9%) — a +5.4pp improvement, consistent with your backtest delta. PnL impact is positive but small, as the removed trades were both small-lot and one was already a loss. OVER-TIME PROJECTION: Over 3–6 months, this filter should reduce noise from low-confirmation entries, which tend to fire during choppy, low-liquidity sessions. Expect win rate to stabilize aroun Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com