Fingerprint has announced the addition of AI-powered recommendations to its Suspect Score solution, marking a significant step forward in adaptive fraud detection.
The enhancement comes in response to the growing inadequacy of static scoring models, which are increasingly unable to keep pace with dynamic, traffic-specific fraud patterns. Fraud teams have historically lacked the time and resources to continuously analyse signal interactions and fine-tune model weights to meet their unique operational needs.
Fingerprint specialises in device intelligence for fraud prevention, providing enterprise fraud and security teams with actionable, real-time insights through its suite of Smart Signals. The platform enables organisations to identify and respond to fraudulent activity with greater precision and speed.
The upgraded Suspect Score introduces a production-ready machine learning (ML) system that allows customers to upload labelled fraud data to train the model on their specific traffic patterns. The system intelligently analyses customer data alongside Smart Signals to generate optimised signal weights tailored to individual fraud profiles, adjusts those weights to reduce false positives while maintaining accuracy, and provides a preview of all recommendations before any changes are applied — giving users full visibility and control at every stage.
As threats evolve, organisations can retrain their scoring models using up-to-date data to keep detection aligned with real-world fraud behaviour. The solution is designed to address the growing challenge posed by sophisticated AI agents and bots capable of bypassing static detection models, as well as the increasing adoption of privacy tools such as VPNs by legitimate users, which can complicate traditional signal weighting.
AI-powered Suspect Score recommendations are now available to all Fingerprint customers with access to Smart Signals. Existing customers can begin training customised scoring models directly through the Fingerprint dashboard.
Fingerprint CTO and co-founder Valentin Vasilyev said, “Fraud patterns vary by business and evolve constantly, rendering manual tuning obsolete. Our AI-powered recommendations remove that bottleneck by training on each customer’s labeled data, making Suspect Score customizable, accurate, and easy for customers to use.”
Keep up with all the latest RegTech news here
Copyright © 2026 RegTech Analyst
Copyright © 2018 RegTech Analyst
