LexisNexis Debuts Self-Calibrating AI to Combat Rising Fraud

The architecture analyzes diverse signals—including email history, IP addresses, and phone data—to create tailored risk models. In internal testing, the system captured roughly 90% of fraud within high-risk transactions while simultaneously cutting false positives by more than 80%. Unlike legacy systems requiring manual policy adjustments, this platform continuously incorporates industry trends and emerging threat patterns to refine its predictive accuracy in real time.

Dell Technologies, an early adopter of the solution, reported doubling its high-risk capture rates while reducing manual reviews of low-risk transactions by 83%. Jeremy Cole, director of business operations at Dell, noted that the automation allows his team to shift away from static rule-sets, enabling them to approve legitimate customer transactions with greater confidence. Kimberly Sutherland, global head of fraud and identity at LexisNexis, emphasized that as generative AI accelerates the velocity of attacks, manual prevention strategies can no longer keep pace. By removing the lag between the emergence of a new threat and system calibration, the technology aims to provide a more responsive defense layer across account management and payment sectors.