Machine Learning Partners in Criminal Networks

Abstract

Recent research has shown that criminal networks have complex organizational structures, but whether this can be used to predict static and dynamic properties of criminal networks remains little explored. Here, by combining graph representation learning and machine learning methods, we show that structural properties of political corruption, police intelligence, and money laundering networks can be used to recover missing criminal partnerships, distinguish among different types of criminal and legal associations, as well as predict the total amount of money exchanged among criminal agents, all with outstanding accuracy. We also show that our approach can anticipate future criminal associations during the dynamic growth of corruption networks with significant accuracy. Thus, similar to evidence found at crime scenes, we conclude that structural patterns of criminal networks carry crucial information about illegal activities, which allows machine learning methods to predict missing information and even anticipate future criminal behavior.

arXiv comment10 pages, 4 figures, supplementary information; accepted for publication in Scientific Reports

References in corpus (10)

• DeepWalk: Online Learning of Social Representations
• LINE: Large-scale Information Network Embedding
• Social physics
• Statistical physics of crime: A review
• A network approach to cartel detection in public auction markets
• The web of federal crimes in Brazil: topology, weaknesses, and control
• Complexity science approach to economic crime
• The Bouncer Problem: Challenges to Remote Explainability
• A Survey on Graph Representation Learning Methods
• A Survey of Explainable Graph Neural Networks: Taxonomy and Evaluation Metrics

Cited by in corpus (5)

• Deep Learning Criminal Networks
• Enhancing Imbalance Learning: A Novel Slack-Factor Fuzzy SVM Approach
• Structural roles and gender disparities in corruption networks
• Improving Demand Forecasting in Open Systems with Cartogram-Enhanced Deep Learning
• Bipartite structure and dynamics of political corruption networks