Saved in:
Bibliographic Details
Main Authors: Imhof, David, Viklund, Emanuel W, Huber, Martin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.12369
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915394884730880
author Imhof, David
Viklund, Emanuel W
Huber, Martin
author_facet Imhof, David
Viklund, Emanuel W
Huber, Martin
contents We propose a novel application of graph attention networks (GATs), a type of graph neural network enhanced with attention mechanisms, to develop a deep learning algorithm for detecting collusive behavior, leveraging predictive features suggested in prior research. We test our approach on a large dataset covering 13 markets across seven countries. Our results show that predictive models based on GATs, trained on a subset of the markets, can be effectively transferred to other markets, achieving accuracy rates between 80% and 90%, depending on the hyperparameter settings. The best-performing configuration, applied to eight markets from Switzerland and the Japanese region of Okinawa, yields an average accuracy of 91% for cross-market prediction. When extended to 12 markets, the method maintains a strong performance with an average accuracy of 84%, surpassing traditional ensemble approaches in machine learning. These results suggest that GAT-based detection methods offer a promising tool for competition authorities to screen markets for potential cartel activity.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12369
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Catching Bid-rigging Cartels with Graph Attention Neural Networks
Imhof, David
Viklund, Emanuel W
Huber, Martin
Econometrics
We propose a novel application of graph attention networks (GATs), a type of graph neural network enhanced with attention mechanisms, to develop a deep learning algorithm for detecting collusive behavior, leveraging predictive features suggested in prior research. We test our approach on a large dataset covering 13 markets across seven countries. Our results show that predictive models based on GATs, trained on a subset of the markets, can be effectively transferred to other markets, achieving accuracy rates between 80% and 90%, depending on the hyperparameter settings. The best-performing configuration, applied to eight markets from Switzerland and the Japanese region of Okinawa, yields an average accuracy of 91% for cross-market prediction. When extended to 12 markets, the method maintains a strong performance with an average accuracy of 84%, surpassing traditional ensemble approaches in machine learning. These results suggest that GAT-based detection methods offer a promising tool for competition authorities to screen markets for potential cartel activity.
title Catching Bid-rigging Cartels with Graph Attention Neural Networks
topic Econometrics
url https://arxiv.org/abs/2507.12369