How Can Fraud Models Combat New Tricks?

A “bolt-on” adaptive model layer, which self-learns new fraud patterns, boosts detection performance.

Superior fraud detection is based on analyzing the abundance of past transactional and case disposition data that goes into building and finely tuning neural network models and other advanced analytics. But financial institutions are always looking for ways to combat newer fraud schemes-schemes that arise between fraud model developments.

One way to boost the performance of fraud models, and sustain it longer, is to add a second layer of adaptive, or self-learning analytics.

Adaptive models bring the perspective of the present and near- present—what is currently happening in the portfolio’s operational environment—to fraud detection.