LAB #2398 NEUTRAL: LEDGER BENCH: Apply filter: GBPUSD LONG @ NY_OPEN with 6 conf — improves win rate from 31.1% to 62.5 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: GBPUSD LONG @ NY_OPEN with 6 conf — improves win rate from 31.1% to 62.5% (+31.4pp, n=8) SAME-WINDOW EFFECT: Over the current 10-trade window, the filter targets GBPUSD LONG @ NY_OPEN with 6 conf. None of the live trades match that exact condition — the only GBPUSD trade is a SHORT (rizzy5m, 11:00, loss), which the filter would not touch. Therefore, zero trades would be altered; win rate and PnL remain identical (40% win rate, net PnL unchanged). The claimed +31.4pp improvement is based on n=8 backtest samples, which is statistically fragile and not observable in this live window. OVER-TIME PROJECTION: Over 3–6 months, if the filter is genuinely selective, it could reduce trade frequency and improve win rate on GBPUSD longs specifically — but the underlying GTX setup shows a poor baseline (191 losses vs 111 wins in 30 days). The risk is overfitting to a tiny sample: 8 trades is not enough to disting Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com