LAB #3963 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.5% to 38.1% (+5.6pp, — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 6 — improves win rate from 32.5% to 38.1% (+5.6pp, n=817) SAME-WINDOW EFFECT: Applying a minimum-6-confirmation filter would have blocked the two rizzy5m entries (AUDUSD SHORT and NZDUSD SHORT) that were rejected or closed as losses, plus the XAUUSD SHORT loss. That removes 3 trades from the window, all of which were losses or rejects, leaving the remaining 7 trades with a win rate of 2/7 (28.6%) — actually worse than the unfiltered 3/10 (30%) if you count the open NZDUSD as a potential win. However, the filter would have eliminated the two clear losses (XAUUSD, NZDUSD rizzy5m) and the rejected AUDUSD, so the net PnL impact is positive by avoiding those negative outcomes, though the small sample makes the win-rate delta unreliable. OVER-TIME PROJECTION: Over 3-6 months, a 6-confirmation filter should reduce false signals from low-conviction entries, likely improving win rate by 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: W7221433099
Cites:
Cited by:
Related to: