Learning from sanctioned government suppliers: A machine learning and network science approach to detecting fraud and corruption in Mexico

TL;DR

This paper introduces a machine learning approach using positive-unlabeled learning and network analysis to detect likely corrupt contracts in Mexico's public procurement, outperforming traditional red flag methods.

Contribution

It develops a novel PU learning framework that combines domain knowledge and network features to identify corrupt contracts without needing confirmed negatives.

Findings

PU model captures 32% more positives than random guessing

Network features like eigenvector centrality are highly influential

Traditional red flags improve model performance mainly for competitive tenders

Abstract

Detecting fraud and corruption in public procurement remains a major challenge for governments worldwide. Most research to-date builds on domain-knowledge-based corruption risk indicators of individual contract-level features and some also analyzes contracting network patterns. A critical barrier for supervised machine learning is the absence of confirmed non-corrupt, negative, examples, which makes conventional machine learning inappropriate for this task. Using publicly available data on federally funded procurement in Mexico and company sanction records, this study implements positive-unlabeled (PU) learning algorithms that integrate domain-knowledge-based red flags with network-derived features to identify likely corrupt and fraudulent contracts. The best-performing PU model on average captures 32 percent more known positives and performs on average 2.3 times better than random guessing, substantially outperforming approaches based solely on traditional red flags. The analysis of the Shapley Additive Explanations reveals that network-derived features, particularly those associated with contracts in the network core or suppliers with high eigenvector centrality, are the most important. Traditional red flags further enhance model performance in line with expectations, albeit mainly for contracts awarded through competitive tenders. This methodology can support law enforcement in Mexico, and it can be adapted to other national contexts too.