LAB #2373 NEUTRAL: LEDGER BENCH: Apply filter: NZDUSD LONG @ NY_OPEN with 6 conf — improves win rate from 31.2% to 87.5 — 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 31.2% to 87.5% (+56.3pp, n=16) SAME-WINDOW EFFECT: Over the current live window, no NZDUSD trades are present, so this filter would have changed zero outcomes. The claimed +56.3pp win-rate improvement is based on n=16 — a sample so small that two flipped outcomes would erase the edge. Against the 10 live trades listed, the filter is irrelevant; it neither helps nor hurts the realized PnL. The only measurable effect would be a reduction in future NZDUSD entries, which could have avoided some losses but also skipped wins not shown here. OVER-TIME PROJECTION: Over 3–6 months, a filter that only fires on NZDUSD LONG at NY_OPEN with 6 conf will likely produce fewer than 20 trades — far too few to validate a 56pp edge. The base win rate of 31.2% suggests the underlying signal is weak; cherry-picking a narrow time/session slice risks overfitting to Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com