Founded in 1937, Michigan State University Federal Credit Union offers financial services to students, faculty and staff of Michigan State University. With over $4.1 billion in assets and 265,000 members, MSUFCU is the largest university-based credit union in the world.

In the past year, U.S. consumers experienced over $8 billion in losses due to payment card fraud. MSUFCU protects its members from fraud by monitoring almost 40 million transactions of its members annually.

Our Transaction Anomaly Detection system leverages the MSUFCU’s existing software platforms to notify its members of unusual account activity.

When anomalous transactions are detected, our system sends push notifications to MSUFCU members and flags the transactions on our companion web app used by MSUFCU associates.

Our system identifies irregularities ranging in severity from a peculiar increase in a monthly cable bill to a suspected account takeover.

In addition to detecting suspicious account activity, our system harnesses a member’s transaction data to provide them with insights into their spending habits.

Within the MSUFCU member web portal, transactions flagged as suspicious can be expanded for more information. Spending habits are summarized by personally tailored reports, which categorize purchases and visualize patterns.

Our Transaction Anomaly Detection iOS, Android and web apps connect to a Django server via a RESTful API. Anomalies are detected using a machine learning TensorFlow module and other scientific Python packages.

Our Transaction Anomaly Detection iOS, Android and web apps connect to a Django server via a RESTful API. Anomalies are detected using a machine learning TensorFlow module and other scientific Python packages.