Machine learning with screens for detecting bid-rigging cartels

Abstract

We combine machine learning techniques with statistical screens computed from the distribution of bids in tenders within the Swiss construction sector to predict collusion through bid-rigging cartels. We assess the out of sample performance of this approach and find it to correctly classify more than 84% of the total of bidding processes as collusive or non-collusive. We also discuss tradeoffs in reducing false positive vs. false negative predictions and find that false negative predictions increase much faster in reducing false positive predictions. Finally, we discuss policy implications of our method for competition agencies aiming at detecting bid-rigging cartels.