LAB #2524 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=1410) SAME-WINDOW EFFECT: Applying a minimum-5-confirmations filter would have rejected the two earliest live trades in the window — the USDCHF SHORT (still open/rejected) and the GBPUSD SHORT at 10:10 (which closed as a WIN). That would have removed one winning trade from the sample, slightly lowering the live win rate in this window (from 5/9 to 4/8, or ~50% to 50% — no net change in win rate, but PnL would drop by the profit of that GBPUSD win). The filter would not have touched the other seven trades, so the immediate effect is marginal and mixed — it removes a winner but also avoids a potentially risky open position. Net PnL delta is slightly negative in this specific window, but the sample is too small to be meaningful. OVER-TIME PROJECTION: Over 3–6 months, a 5-confirmation minimum should reduce noise entries triggered Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com