Mihály Fazekas, DPP professor, has published a co-authored paper with CEU alumni on using machine learning for detecting cartels in public procurement

Mihály Fazekas has published co-authored paper with CEU alumni, Bence Tóth, Johannes Wachs, and Aly Abdou on using machine learning for detecting cartels in public procurement in the International Journal of Industrial Organization. The article addresses the daunting challenge of identifying and countering price fixing, bid rigging and collusion among public procurement bidders across Europe. The article advances on prior literature which developed cartel measurement methods that work well for narrow and well-defined cartel types and with high quality data, but it didn’t produce generalisable knowledge supporting policy and law enforcement on typically available datasets. The authors simultaneously measure multiple cartel behaviours on publicly available data of 73 cartels from 7 European countries covering 2004–2021. We apply machine learning methods, using diverse cartel screens characterising pricing and bidding behaviours in a predictive model. Combining many indicators in a random forest algorithm achieves 70–84 % prediction accuracy, distinguishing behavioural traces of confirmed cartels from non-cartels across different cartel types and countries (accuracy is 97 % when trained and tested on a single cartel case, typical of the literature). Most screens contribute to prediction in line with theory. These results have the potential to improve cartel detection and investigations and support pro-competition policies. These policy implications are being currently explored in collaboration with a number of competition authorities across Europe.