SPOTLIGHT PRESENTATION: MACHINE LEARNING IN FRAUD DETECTION - STRATEGY, DESIGN & OVERSIGHT

As fraud tactics grow more sophisticated, traditional rule-based detection systems struggle to keep up with the speed and complexity of modern threats. Machine learning offers a powerful new approach - one that adapts in real time, identifies subtle patterns, and scales with your enterprise. But implementing ML for fraud detection isn't just a plug-and-play solution; it requires thoughtful design, constant tuning, and cross-functional oversight to ensure accuracy, explainability, and compliance.

This event will explore how organizations can move from reactive detection to proactive prevention by embedding ML across key touch points in the fraud lifecycle. It will also examine core model design strategies, data challenges, governance requirements, and best practices for managing these systems at scale - turning risk management into a competitive advantage.

Topics of discussion will include, yet will not be limited to:

• ML in Action - how supervised and unsupervised models detect known and emerging fraud patterns
• System Design & Data Strategy - what it takes to build and train fraud models that evolve
• Managing for Accuracy, Bias & Compliance - operationalizing fraud ML in regulated, high-risk environments

SriHarsha Anand Pushkala, Director, Fraud Strategy & Analytics, ATLANTICUS