Machine Learning for Detecting Collusion and Capacity Withholding in Wholesale Electricity Markets

TL;DR

This paper demonstrates that machine learning algorithms, especially ensemble methods with novel capacity-withholding screens, can effectively detect collusion in electricity markets, achieving up to 98% accuracy in classifying tenders.

Contribution

It introduces new capacity-withholding screens derived from market data and evaluates their impact on cartel detection accuracy in electricity markets.

Findings

Up to 95% accuracy in classifying tenders as collusive or competitive.

Including capacity-withholding screens improves detection in complete cartels.

Existing screens suffice for incomplete cartels with larger datasets.

Abstract

Collusion and capacity withholding in electricity wholesale markets are important mechanisms of market manipulation. This study applies a refined machine learning-based cartel detection algorithm to two cartel cases in the Italian electricity market and evaluates its out-of-sample performance. Specifically, we consider an ensemble machine learning method that uses statistical screens constructed from the offer price distribution as predictors for the incidence of collusion among electricity providers in specific regions. We propose novel screens related to the capacity-withholding behavior of electricity providers and find that including such screens derived from the day-ahead spot market as predictors can improve cartel detection. We find that, under complete cartels - where collusion in a tender presumably involves all suppliers - the method correctly classifies up to roughly 95% of tenders in our data as collusive or competitive, improving classification accuracy compared to using only previously available screens. However, when trained on larger datasets including non-cartel members and applying algorithms tailored to detect incomplete cartels, the previously existing screens are sufficient to achieve 98% accuracy, and the addition of our newly proposed capacity-withholding screens does not further improve performance. Overall, this study highlights the promising potential of supervised machine learning techniques for detecting and dismantling cartels in electricity markets.