On suspicious tracks: machine-learning based approaches to detect cartels in railway-infrastructure procurement

TL;DR

This paper introduces machine-learning methods to detect potential collusion in railway infrastructure procurement, utilizing a unique Swiss dataset to identify suspicious bidding patterns and develop a decentralized screening tool.

Contribution

It pioneers the application of machine-learning based price screening techniques to railway-infrastructure markets for collusion detection.

Findings

Machine learning effectively identifies suspicious bidding patterns.

A novel category-managers' tool enables decentralized screening.

First application of ML-based collusion detection in railway procurement.

Abstract

In railway infrastructure, construction and maintenance is typically procured using competitive procedures such as auctions. However, these procedures only fulfill their purpose - using (taxpayers') money efficiently - if bidders do not collude. Employing a unique dataset of the Swiss Federal Railways, we present two methods in order to detect potential collusion: First, we apply machine learning to screen tender databases for suspicious patterns. Second, we establish a novel category-managers' tool, which allows for sequential and decentralized screening. To the best of our knowledge, we pioneer illustrating the adaption and application of machine-learning based price screens to a railway-infrastructure market.