Machine learning models help Metro Bank achieves 71% uplift in mule payment detection to meet PSR regulations

7 Pages

LexisNexis helped Metro Bank get PSR‑ready by deploying custom machine learning models and consortium intelligence to detect mule payments in near real time, lifting historic mule detection volumes by 71%. By combining Digital Identity Network data, transactional patterns, and beneficiary account intelligence, the solution identified over 2.5 million in outgoing proceeds‑of‑fraud in six months and flagged 13% of suspicious accounts as confirmed mules, significantly reducing potential PSR reimbursement exposure that could otherwise have reached about 5 million annually.

Join for free to read

Case Study Fraud Detection with In-Memory Machine Learning

Case Study BANK OF THAILAND (BOT) REGULATIONS AND GUIDELINES

Report The Market for Proactive Mule Detection: A Sea Change in the…

Case Study MACHINE LEARNING APPLICATIONS HELP TOP-20 EUROPEAN BANK MEET…

More from LexisNexis Risk Solutions

White Paper The Multi-Layer Fraud Defense Network A More Holistic Approach…

White Paper Top Five Ways to Help Reduce the Cost of Insurance Identity Fraud

White Paper Detecting the Undetectable: What personal lines carriers are…

Case Study The LexisNexis® ThreatMetrix® Solution Supports Commercial Bank…

Case Study

Machine learning models help Metro Bank achieves 71% uplift in mule payment detection to meet PSR regulations

Machine learning models help Metro Bank achieves 71% uplift in mule payment detection to meet PSR regulations

You Might Also Like

More from LexisNexis Risk Solutions