LAB #2077 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 32.0% to 33.6% (+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 32.0% to 33.6% (+1.6pp, n=1351) SAME-WINDOW EFFECT: Over the current live window, applying a minimum-confirmation filter of ≥5 would have blocked the XAUUSD SHORT entries at 4048.74 and 4051.79 (both losses) and likely the 4066.35 loss as well, depending on confirmation timing. It would also have filtered the GBPUSD SHORT at 1.34508 (loss) if confirmations were below threshold. That removes 3–4 losing trades from a 10-trade sample, shifting the live win rate from roughly 50% (5/10) to ~70–83% (5–6/7), with a clear positive PnL delta. However, the sample is tiny and includes one open trade, so the effect is directionally supportive but not statistically meaningful. OVER-TIME PROJECTION: Over 3–6 months, a +1.6pp win-rate improvement from n=1351 suggests a modest but real edge, likely by cutting low-conviction entries that fail more often. The risk is th Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com