LAB #3920 NEUTRAL: 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=1805) SAME-WINDOW EFFECT: Applying a min-confirmations filter of ≥5 would have blocked the two rizzy5m entries (AUDUSD SHORT, NZDUSD SHORT) and likely the rizzy7m entries (EURJPY, EURUSD, USDCHF, GBPUSD) if they had fewer than 5 confirmations at entry — though we lack per-trade confirmation counts. In the visible window, the blocked rizzy5m trades were 1 loss and 1 open/rejected, while the rizzy7m set included 2 wins and 3 losses; net effect is ambiguous but likely removes low-quality noise, improving win rate modestly (maybe +0.5–1.0pp) without major PnL shift. OVER-TIME PROJECTION: Over 3–6 months, a stricter confirmation filter typically reduces trade frequency by 15–25%, which can lower total PnL even if win rate rises — especially if filtered-out trades include occasional high-RR winners. Risk: the +1.5pp backtest gain ma Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com