LAB #1206 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.6% to 41.2% (+9.6pp, — 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 31.6% to 41.2% (+9.6pp, n=323) SAME-WINDOW EFFECT: Applying a minimum 6 confirmations filter would have rejected the EURUSD SHORT via rizzy5m (entry at 1.13594, currently CLOSED/open) and the USDJPY SHORT via wkjudas (entry at 163.796, REJECTED/open), as these likely had fewer confirmations at entry. The NZDUSD LONG via wkjudas (entry at 0.57702, REJECTED/open) would also likely be filtered out. This would remove three trades from the window, two of which were already rejected or unclear in outcome, so the immediate PnL delta is negligible but the win-rate would shift upward by removing lower-confidence entries. OVER-TIME PROJECTION: Over 3-6 months, the filter should reduce the number of low-conviction trades that drag down win rate, potentially sustaining the +9.6pp improvement seen in backtests. However, the risk is that it may also filter out some 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: W7203889967
Cites:
Cited by:
Related to: