Using AI for Scalable, Supercharged Fraud Detection in Financial Services

WEBINAR ON DEMAND

Duration: 30 minutes

Digital fraud is evolving rapidly, becoming more complex and harder to detect. Recent estimates forecast that payment fraud will exceed $362 billion between 2023 and 2028, with remote purchases of physical goods accounting for over 47 percent of fraud losses¹. By 2026, financial losses from global credit card transaction fraud alone are expected to reach $43 billion². This is just one of the many threats financial institutions must address, others include identity theft, account takeovers, authorized push payment fraud, check scams, and more.

Traditional methods of fraud detection, including rules-based systems, statistical modeling, and manual reviews, struggle to keep pace with the scale and sophistication of modern threats. Fraud detection powered by artificial intelligence (AI) offers a transformative solution, enabling financial institutions to stay ahead of evolving fraud tactics. During this discussion, AWS and NVIDIA industry experts will share insights on how financial institutions can harness AI to strengthen fraud detection. Learn how to:

• Identify subtle patterns and anomalies in transaction data based on user behavior to improve detection accuracy and reduce false positives
• Deploy accelerated computing infrastructure to manage increasing data volumes
• Utilize modern technologies, like graph neural networks and transformer architectures, to further enhance AI-powered fraud detection systems

1 “Online Payment Fraud: Emerging Threats, Segment Analysis, & Market Forecasts 2023-2028,” Juniper Research, June 2023

2 “Card Fraud Losses Worldwide — 2021,” Nilson Report, December 2022