Hunting Money Mules:
A Deep Dive into Fraud Networks
Stop the mules, stop the fraud
In the ever-evolving landscape of digital banking, fraudsters continually devise new methods to obscure their illicit activities. One such method involves the use of money mules—individuals who receive and transfer stolen funds on behalf of criminals.
In this article, we explore the intricacies of money mule networks and how financial institutions can combat this growing threat. Sheldon West, Head of Data Science and Analytics at LexisNexis® Risk Solutions explains how criminals are using money mules to exit fraudulent assets from banks and payment service providers, and how organisations can take preventative measures.
What is a Money Mule?
A money mule is an individual whose bank account is used to receive and transfer fraudulent funds. Fraudsters leverage these accounts to distance themselves from the crime, making it harder for authorities to trace the illicit money back to them. The speed and obfuscation of transactions are critical, with funds often layered through multiple accounts to evade detection.
The Role of Mule Herders
Mule herders are key players in these networks, responsible for recruiting and managing money mules. They use various tactics, including job adverts, social media, romance scams, and even coercion, to enlist individuals. Once recruited, mules are often kept in line through blackmail or other manipulative tactics.
The Regulatory Landscape
Regulation is tightening, with significant changes like the Payment Systems Regulator (PSR) legislation in the UK driving a liability shift. This change sees the cost of fraud split between the receiving institution and the institution that originally made the payment.
This shift underscores the importance of identifying and mitigating money mule activities to avoid financial penalties, with potentially significant reimbursement and reputational costs for organisations that don’t have effective measures in place to identify and protect against fraud.
Tackling the Issue
Data Collection
Crowdsourced Knowledge Sharing
Pattern Identification
Consortium Collaboration
Machine Learning and Model Features
Machine learning models play a crucial role in detecting money mule activities like in this case study in which Metro Bank successfully achieved a 71% uplift in mule payment detection and projected annual savings of £5 million from potential fraud victim reimbursement costs.
These models analyse various signals across the customer journey, from account creation to transaction behaviours.
Key features include:
- Login Patterns: Frequent logins can suggest a mule anticipating receipt of significant funds that need laundering.
- Transaction Behaviour: Large, rapid transfers following fund receipt are red flags.
- Digital Footprint: Combining data from multiple sources to create a comprehensive view of the mule’s activities.
Metro Bank achieves 71% uplift in mule payment detection ahead of PSR
Discover how Metro Bank, partnering with LexisNexis® Risk Solutions, tackles PSR challenges head-on, achieving impressive results before the October deadline.
Conclusion
Money mule networks are a sophisticated and evolving threat in the financial sector. By adopting a multi-faceted approach that includes data collection, knowledge sharing, and advanced machine learning models, financial institutions can stay ahead of fraudsters. Collaboration across the industry is essential, as shared intelligence significantly enhances the ability to detect and mitigate these threats.
For more detailed insights on money mules and how to stop them, download our eBook Hunting Money Mules with a 360-Degree View of Identity.
