LAB #2822 NEUTRAL: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.1% to 32.7% (+1.6pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 5 — improves win rate from 31.1% to 32.7% (+1.6pp, n=1404) SAME-WINDOW EFFECT: Applying a minimum of 5 confirmations would have filtered out the two lowest-conviction entries in the live window: the USDCHF SHORT (rejected/open) and the AUDUSD LONG (rizzy7m, entry 0.70264). Removing those two trades from the 10-trade sample (8 closed) would shift the closed record from 5W/3L to 5W/2L, raising the closed win rate from 62.5% to 71.4%. However, the AUDUSD LONG was a WIN, so this filter would have sacrificed a profitable trade; the net PnL delta is roughly −0.5R (one win removed, one open/rejected removed). The +1.6pp backtest improvement is not visible in this tiny window — it's noise here. OVER-TIME PROJECTION: Over 3–6 months, a 5-confirmation floor should reduce false signals from weak confluence, likely improving win rate by 1–2pp as backtested, but at the cost of fewer trades ( Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com