LAB #2913 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.1% to 37.7% (+6.6pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 6 — improves win rate from 31.1% to 37.7% (+6.6pp, n=432) SAME-WINDOW EFFECT: Applying a minimum of 6 confirmations would have filtered out the weakest-signal trades. In the current window, the two losses from `rizzy5m` (GBPUSD 1.34508, XAUUSD 4051.79) and the `wkjudas` loss (USDJPY) likely had fewer confirmations — removing them would have eliminated 3 losses while keeping all 5 wins, shifting the window from 5W/5L to 5W/2L (71.4% win rate vs. 50%). The rejected USDCHF trade would also likely be dropped, reducing exposure. Expected PnL delta: roughly +2.5R to +3R on this small sample, consistent with the +6.6pp backtest gain. OVER-TIME PROJECTION: Over 3–6 months, this filter should raise win rate from ~31% toward ~38%, but the trade count will drop — likely by 20–30% — which may reduce total net profit if average win size doesn't compensate. The main risk is overfitting to a s Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com