LAB #2119 NEUTRAL: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — 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: Pool density HIGH (>=90) — improves win rate from 32.0% to 33.6% (+1.6pp, n=1354) SAME-WINDOW EFFECT: Applying the pool-density filter (>=90) would have excluded the XAUUSD SHORT at 4048.74 (11:35) and the XAUUSD SHORT at 4051.79 (07-31), both closed as losses. It would also have excluded the EURJPY LONG at 187.042 (07-29, WIN) and GBPUSD LONG at 1.33621 (07-29, WIN) — removing two winners. Net effect on the 10-trade window: 2 losses removed, 2 wins removed, leaving 6 trades with 2 wins and 4 losses (33% win rate vs. current 40%). PnL delta is roughly neutral to slightly negative, as the removed losses may be larger than the removed wins, but the sample is too small to confirm the +1.6pp edge. OVER-TIME PROJECTION: Over 3–6 months, the filter's +1.6pp win-rate gain (n=1354) is statistically marginal (p≈0.08) and likely driven by a specific regime (e.g., high-volatility or high-correlation periods). Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com