Observed arrival · 2026-09-19
Algorithmic Antitrust: An Audit Engine for Pricing Algorithms
A specialized auditing engine that tests pricing data for lockstep movement, machine-speed following, asymmetric responses, delegated recommendations, and competitor-data commingling.
- For
- Antitrust counsel, compliance teams, and pricing-system operators
- Worth noticing
- It searches short lag bands and reports both correlation and Granger-causality measures, while labeling level correlation spurious-prone.
Field notes
The audit accepts either private execution records or public merchant price snapshots, with optional fields for recommendations, overrides, and input features. Its documented tests include short-window and seven-day co-movement, bidirectional Granger causality, event reaction time, asymmetric pass-through, and acceptance streaks. Results are described as indices with p-values against three calibrated competitive simulations, accompanied by a read-only SHA-256 evidence chain.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue