Fingerprint has introduced Fraud Score, a predictive signal that builds fraud models from each customer’s own fraud outcomes. In one head-to-head trial it detected nearly 50% more fraud than a client’s in-house model.
The new tool combines Fingerprint’s device intelligence with its machine learning capabilities to learn the specific fraud patterns affecting each organisation. Businesses can therefore improve detection accuracy without building and maintaining models internally.
In the comparative evaluation, the gain in caught fraud came without any rise in the number of legitimate users being blocked.
Fingerprint argues that fraud is increasingly sophisticated, leaving security and risk teams with a growing volume of signals that must be turned into reliable decisions. Many existing tools handle fraud as a single problem, yet threats such as account takeover (ATO), payment fraud, promotion abuse and fake account creation behave differently and demand tailored detection.
Generic risk scores miss these distinctions, so engineering and fraud teams lose time to manual investigation, rule writing and continual model upkeep.
Fraud Score addresses this by merging Fingerprint’s wide range of device signals with outcome data supplied by each client, producing models fitted to that organisation’s traffic. Teams can act on the predictions directly or feed them into existing decisioning systems through Fingerprint’s API responses. As customers submit fresh outcomes, Fingerprint retrains the models on an ongoing basis.
The company positions the product against alternatives that depend on generalised network rules or require in-house data scientists to run their own prediction layers. Fraud Score maintains separate models for distinct threats, including payment fraud, ATO, multi-accounting, fake account creation, promotion abuse, platform abuse and content abuse.
Its predictions draw on each client’s own fraud results, and its use of device intelligence surfaces correlations and anomalies that manual rules tend to overlook.
Fingerprint VP of product Catherine Woneis said, “Fraud teams have a signal-to-decision problem. We built Fraud Score to give every organization the power of custom machine learning without the complexity of building and maintaining custom models. Fraud Score trains specialized models on each customer’s actual fraud outcomes and our device intelligence, enabling teams to stop specific threats with far greater precision.”
Copyright © 2026 RegTech Analyst
Copyright © 2026 RegTech Analyst
