By Martin Huber
We combine machine learning techniques with statistical screens computed from the distribution of bidsin 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 80% of the total of bidding processes as collusive or non-collusive. As the correct classification rate, however, differs across truly non-collusive and collusive processes, we also investigate tradeoffs in reducing false positive vs. false negative predictions. Finally, we discuss policy implications of our method for competition agencies aiming at detecting bid-rigging cartels.
Featured News
T-Mobile Faces Class-Action Lawsuit Over Sprint Merger After Appeal Denied
May 16, 2024 by
CPI
Google Faces Backlash Over Introduction of AI-Generated Summaries in Searches
May 16, 2024 by
CPI
CMA Launches Phase 2 Probe into AlphaTheta’s Acquisition of Serato
May 16, 2024 by
CPI
NFL Executive Escapes Testifying in High-Stakes Trial Over Televised Games
May 16, 2024 by
CPI
EU Consumers Lodge Complaint Against Chinese Retailer Temu Over Content Rules Breach
May 16, 2024 by
CPI
Antitrust Mix by CPI
Antitrust Chronicle® – Ecosystems
May 9, 2024 by
CPI
Mapping Antitrust onto Digital Ecosystems
May 9, 2024 by
CPI
Ecosystems and Competition Law: A Law and Political Economy Approach
May 9, 2024 by
CPI
Ecosystem Theories of Harm: What is Beyond the Buzzword?
May 9, 2024 by
CPI
Open Ecosystems: Benefits, Challenges, and Implications for Antitrust
May 9, 2024 by
CPI