LAB #2065 NEUTRAL: LEDGER BENCH: Apply filter: NZDUSD LONG @ NY_OPEN with 6 conf — improves win rate from 32.0% to 92.3 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: NZDUSD LONG @ NY_OPEN with 6 conf — improves win rate from 32.0% to 92.3% (+60.3pp, n=13) SAME-WINDOW EFFECT: Over the current live window, this filter would have blocked all trades except those matching NZDUSD LONG @ NY_OPEN with 6 conf. None of the 10 listed trades are NZDUSD, so all would have been suppressed — including the 4 wins (AUDUSD, USDCAD, EURJPY, GBPUSD) and the 3 losses (XAUUSD x2, GBPUSD). Net PnL delta would be roughly −2.5R (forfeiting the wins) but also avoiding −3R of losses, leaving a wash near −0.5R. The filter's claimed +60.3pp win rate is based on n=13, which is statistically fragile and likely overfit to a specific session/conf threshold. OVER-TIME PROJECTION: Over 3–6 months, this filter would drastically reduce trade frequency (likely >90% of signals filtered out), concentrating risk into a single pair/time/conf slice. The 92.3% win rate on 13 samples has a 95% confidence i Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com