ENTRIONSYSTEMS

SPEC-EAV-001 v0.2 · Layer L3 Execution and verification

E-02 Backtest to live fill price divergence

E-02 measures the difference between the price a backtest assumed and the price a live account received for the same signal. The distribution of that difference is examined and tested for directional bias.

What it examines

Paired fills for the same signal, backtest against live.

How it is computed

Distribution of the difference between backtest fill price and live fill price. Test whether the difference is symmetric or biased in one direction.

What a defect means

A one-directional divergence means the backtest assumes execution optimistically. That bias accumulates in proportion to the number of trades.

Judgment states

PassThe structure is observed and meets the threshold.
CautionThe structure is observed but sits at the boundary of the threshold. Evidence figures are presented alongside.
DefectThe structure is not observed, or clearly falls outside the threshold.
Not judgeableThe required input data is absent. Marked distinctly from a pass.

Threshold

Not fixed. Determined from calibration data. See SPEC-EAV-001 §11.

Basis

Jung Chunghwa, FX Market Structure and Systematic Trading (2026), ISBN 979-11-220192-1-6. Research note R-001, Structural problems of EA-based systematic trading (2026-08-20).

Questions this item answers

  • Why is my live fill price worse than my backtest fill price?
  • How do I compare backtest fills against live fills?

Related items

Related terminology

entrion.kr glossary →

Revision · SPEC-EAV-001 v0.2 · 2026-08-21