LAB #2098 NEUTRAL: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 32.0% to 33.7% (+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 33.7% (+1.6pp, n=1355) SAME-WINDOW EFFECT: Applying the pool-density HIGH (>=90) filter to the current live window would have excluded trades triggered when pool density was below 90. Of the 10 listed trades, I estimate 3-4 (likely the XAUUSD shorts and possibly the EURJPY LONG) would have been filtered out, removing 2 losses and 1 win. Net effect on this small sample: win rate would shift from 5W/4L (55.6%) to roughly 4W/2L (66.7%), with a modest positive PnL delta of +0.3R to +0.5R, but the sample is too small to be meaningful. OVER-TIME PROJECTION: Over 3-6 months, the +1.6pp win-rate improvement from backtest (n=1355) is statistically weak (p≈0.15) and likely within noise. The filter reduces trade frequency (fewer setups), which could lower total PnL even if win rate rises slightly, especially if filtered-out trades include occasional la 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: W7212378805
Cites:
Cited by:
Related to: