LAB #1842 NEUTRAL: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 32.0% to 33.6% (+1.6pp — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: 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=1348) SAME-WINDOW EFFECT: Applying the pool-density filter (≥90) would have excluded the three rizzy5m XAUUSD shorts and the AUDUSD short, as those likely occurred in lower-density pools. That removes 4 trades from the 10 listed, all of which were losses or open/rejected — eliminating at least 2 confirmed losses and likely improving the window's net PnL. The remaining rizzy5m EURJPY short (win) and the other signals (wkjudas, sqz, rizzy) would stay, so the win rate in this sample would rise from ~50% (5/10) to ~83% (5/6) if we count only closed trades. Expected PnL delta: positive, roughly +2R to +3R over this window, though sample size is tiny. OVER-TIME PROJECTION: Over 3–6 months, a +1.6pp win-rate gain at n=1348 is statistically marginal (p ≈ 0.08–0.12), so it may be real but weak. The filter likely reduces trade frequen Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Author: Caldin, Andrew Stewart
Language: English
Subfield: Finance
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7208805952
Cites:
Cited by:
Related to: