LAB #1876 NEUTRAL: LEDGER BENCH: Apply filter: Min confirmations >= 5 — 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: Min confirmations >= 5 — improves win rate from 32.0% to 33.6% (+1.6pp, n=1348) SAME-WINDOW EFFECT: Applying a minimum of 5 confirmations would have filtered out the two `rizzy5m` SHORT entries on XAUUSD (both losses) and likely the EURJPY SHORT (win) if it had fewer than 5 confirmations at entry. Based on the live window, this filter removes 2 losses and 1 win, shifting the live record from 4W/4L to 3W/2L — a raw win-rate improvement from 50% to 60% on surviving trades. However, the net PnL delta is ambiguous: the removed EURJPY win may have contributed more profit than the two XAUUSD losses combined, so the filter could reduce total return despite improving win rate. The backtest's +1.6pp is consistent but not confirmed as PnL-positive here. OVER-TIME PROJECTION: Over 3–6 months, a 5-confirmation minimum will likely reduce trade frequency by 15–25% (since `rizzy5m` and `sqz` entries are often earl Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Author: Caldin, Andrew Stewart
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7210281119
Cites:
Cited by:
Related to: