LAB #4065 PROMISING: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 32.6% to 34.0% (+1.5pp — 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 32.6% to 34.0% (+1.5pp, n=1818) SAME-WINDOW EFFECT: Applying the pool-density filter (≥90) would have excluded the two `wkjudas` entries (GBPUSD LONG, USDJPY SHORT) and likely the `rizzy5m` NZDUSD SHORT and XAUUSD SHORT, as those occurred during low-density or fragmented pool conditions. Of the 10 live trades, 4–5 would have been filtered out, removing 3 losses and 1 open (AUDUSD SHORT), leaving a mix of 1–2 wins and 2–3 losses. Net PnL delta would be positive but modest — roughly +0.8% to +1.2% on the window, driven by avoiding the two clear `wkjudas` losses. The win rate on remaining trades would rise to ~40–50%, but the sample is tiny (n=5–6), so this is not statistically meaningful. OVER-TIME PROJECTION: Over 3–6 months, the filter should lift win rate by ~1.5pp as backtested, but the real gain is variance reduction — fewer low-quality entries du 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: W7221783768
Cites:
Cited by:
Related to: