Fingerprint trains specialized models to detect distinct fraud types

Fingerprint launched Fraud Score, a predictive fraud signal trained on each customer's own fraud outcomes and powered by Fingerprint's device intelligence and machine learning models, the company announced. Fraud Score learns the fraud types specific to each organization so customers can identify fraud more accurately without building and maintaining their own models. Fingerprint framed the launch against a wider range of fraud threats "amplified by AI-powered techniques," arguing basic risk scoring cannot match the many fraud types businesses now face.