MODEL ADOPTION #4171: REJECT — LEDGER BENCH: Apply filter: Session = LONDON_OPEN — improves win rate from 32.6% to 36.2% — E8 Intelligence Research
- 1Independent Researcher, United Kingdom
Abstract
DECISION: REJECT ELEMENT: No single rule survives — the LONDON_OPEN filter is a session heuristic, not an E8 geometry timing constraint. It contradicts the model's core rhythm logic (Gods-Clock) which already encodes session boundaries via phase transitions. Adding a hard filter would double-count time structure and likely discard high-volatility setups that E8 intentionally targets during Asian/New York overlap. EXPECTED IMPACT: +0.0pp win-rate in live — the +3.6pp backtest edge is likely an artifact of n=356 with regime clustering (summer thin liquidity). The live window's neutral PnL delta confirms no real profit gain. Over 3-6 months, the edge would decay to <1pp due to session-boundary drift and slippage, while increasing missed-trade opportunity cost. RISK: Overfitting to a single session; wkjudas and rizzy5m/7m are not session-designed — they rely on momentum bursts that occur across all hours. Filtering to LONDON_OPEN would reduce trade frequency by ~40%, starve the model
Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Related
- MODEL ADOPTION #4140: REJECT — LEDGER BENCH: Apply filter: Session = OFF_SESSION — improves win rate from 32.6% to 42.5% — E8 Intelligence Research
- MODEL ADOPTION #4465: REJECT — LEDGER BENCH: Apply filter: Session = OFF_SESSION — improves win rate from 31.5% to 41.9% — E8 Intelligence Research
- MODEL ADOPTION #4639: REJECT — VIDEO SCOUT: ICT Concepts - London Session Raids 2:00am to 5:00am, New York Local Time — E8 Intelligence Research
- MODEL ADOPTION #4606: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.6% to 35.8% — E8 Intelligence Research
- MODEL ADOPTION #4136: REJECT — LEDGER BENCH: Apply filter: Phase distance TIGHT (<=2deg) — improves win rate from 32.6% t — E8 Intelligence Research
BibTeX
@misc{caldin2026model,
title = {{MODEL ADOPTION #4171: REJECT — LEDGER BENCH: Apply filter: Session = LONDON_OPEN — improves win rate from 32.6% to 36.2% — E8 Intelligence Research}},
author = {Andrew Stewart Caldin},
howpublished = {Zenodo},
year = {2026},
month = oct,
doi = {10.5281/zenodo.23446841},
url = {https://zenodo.org/records/23446841},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - MODEL ADOPTION #4171: REJECT — LEDGER BENCH: Apply filter: Session = LONDON_OPEN — improves win rate from 32.6% to 36.2% — E8 Intelligence Research
AU - Andrew Stewart Caldin
PY - 2026
DA - 2026/10/18
PB - Zenodo
DO - 10.5281/zenodo.23446841
UR - https://zenodo.org/records/23446841
AB - DECISION: REJECT ELEMENT: No single rule survives — the LONDON_OPEN filter is a session heuristic, not an E8 geometry timing constraint. It contradicts the model's core rhythm logic (Gods-Clock) which already encodes session boundaries via phase transitions. Adding a hard filter would double-count time structure and likely discard high-volatility setups that E8 intentionally targets during Asian/New York overlap. EXPECTED IMPACT: +0.0pp win-rate in live — the +3.6pp backtest edge is likely an artifact of n=356 with regime clustering (summer thin liquidity). The live window's neutral PnL delta confirms no real profit gain. Over 3-6 months, the edge would decay to <1pp due to session-boundary drift and slippage, while increasing missed-trade opportunity cost. RISK: Overfitting to a single session; wkjudas and rizzy5m/7m are not session-designed — they rely on momentum bursts that occur across all hours. Filtering to LONDON_OPEN would reduce trade frequency by ~40%, starve the model Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
ER -