LAB #4419 NEUTRAL: LEDGER BENCH: Apply filter: Session = OFF_SESSION — improves win rate from 31.6% to 41.9% (+10.3pp, — E8 Intelligence Research
- 1Independent Researcher, United Kingdom
Abstract
IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = OFF_SESSION — improves win rate from 31.6% to 41.9% (+10.3pp, n=129)
SAME-WINDOW EFFECT: Applying the OFF_SESSION filter would have excluded all trades in the current window, as every entry timestamp falls within standard trading sessions (02:43–15:08 +02:00). The live window shows 4 wins, 3 losses, and 3 open/rejected — a raw win rate of 57% on closed trades, which is already above the unfiltered backtest baseline. If the filter had been live, zero trades would have fired, eliminating both the 4 wins and the 3 losses — net PnL delta would be roughly flat to slightly negative (forgone profits exceed avoided losses). The filter's claimed +10.3pp edge does not manifest here because no OFF_SESSION trades exist in this sample; the window is too small and session-homogeneous to validate.
OVER-TIME PROJECTION: Over 3–6 months, the filter would likely reduce trade frequency by 60–80% (most signal
Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Related
- LAB #4176 NEUTRAL: LEDGER BENCH: Apply filter: Session = OFF_SESSION — improves win rate from 32.6% to 42.5% (+9.9pp, n — E8 Intelligence Research
- LAB #4462 NEUTRAL: LEDGER BENCH: Apply filter: Session = LONDON_OPEN — improves win rate from 31.5% to 34.8% (+3.3pp, n — E8 Intelligence Research
- LAB #4435 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT @ OFF_SESSION with 6 conf — improves win rate from 31.5% to — E8 Intelligence Research
- LAB #4494 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT @ OFF_SESSION with 6 conf — improves win rate from 31.6% to — E8 Intelligence Research
- LAB #4589 NEUTRAL: LEDGER BENCH: Apply filter: Session = NY_OPEN — improves win rate from 31.6% to 38.3% (+6.7pp, n=802 — E8 Intelligence Research
BibTeX
@misc{caldin20264419,
title = {{LAB #4419 NEUTRAL: LEDGER BENCH: Apply filter: Session = OFF_SESSION — improves win rate from 31.6% to 41.9% (+10.3pp, — E8 Intelligence Research}},
author = {Andrew Stewart Caldin},
howpublished = {Zenodo},
year = {2026},
month = oct,
doi = {10.5281/zenodo.23490642},
url = {https://zenodo.org/records/23490642},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - LAB #4419 NEUTRAL: LEDGER BENCH: Apply filter: Session = OFF_SESSION — improves win rate from 31.6% to 41.9% (+10.3pp, — E8 Intelligence Research
AU - Andrew Stewart Caldin
PY - 2026
DA - 2026/10/20
PB - Zenodo
DO - 10.5281/zenodo.23490642
UR - https://zenodo.org/records/23490642
AB - IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = OFF_SESSION — improves win rate from 31.6% to 41.9% (+10.3pp, n=129) SAME-WINDOW EFFECT: Applying the OFF_SESSION filter would have excluded all trades in the current window, as every entry timestamp falls within standard trading sessions (02:43–15:08 +02:00). The live window shows 4 wins, 3 losses, and 3 open/rejected — a raw win rate of 57% on closed trades, which is already above the unfiltered backtest baseline. If the filter had been live, zero trades would have fired, eliminating both the 4 wins and the 3 losses — net PnL delta would be roughly flat to slightly negative (forgone profits exceed avoided losses). The filter's claimed +10.3pp edge does not manifest here because no OFF_SESSION trades exist in this sample; the window is too small and session-homogeneous to validate. OVER-TIME PROJECTION: Over 3–6 months, the filter would likely reduce trade frequency by 60–80% (most signal Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
ER -