Using social network analysis to prevent money laundering

TL;DR

This paper demonstrates that social network analysis can effectively identify risky clients and suspicious activities in money laundering prevention by analyzing real-world factoring data and proposing network-based predictive models.

Contribution

It introduces a novel approach combining network metrics and visual analysis to assess client risk and detect criminal clusters in financial transactions.

Findings

Risk profiles correlate with network centrality and transaction size.

Dangerous actors are more peripheral and operate across sectors and regions.

Network analysis enhances detection of suspicious financial operations.

Abstract

This research explores the opportunities for the application of network analytic techniques to prevent money laundering. We worked on real world data by analyzing the central database of a factoring company, mainly operating in Italy, over a period of 19 months. This database contained the financial operations linked to the factoring business, together with other useful information about the company clients. We propose a new approach to sort and map relational data and present predictive models, based on network metrics, to assess risk profiles of clients involved in the factoring business. We find that risk profiles can be predicted by using social network metrics. In our dataset, the most dangerous social actors deal with bigger or more frequent financial operations; they are more peripheral in the transactions network; they mediate transactions across different economic sectors and operate in riskier countries or Italian regions. Finally, to spot potential clusters of criminals, we propose a visual analysis of the tacit links existing among different companies who share the same owner or representative. Our findings show the importance of using a network-based approach when looking for suspicious financial operations and potential criminals.