# Fingerprint trains specialized models to detect distinct fraud types

DevFeed: [Fingerprint trains specialized models to detect distinct fraud types](<https://devfeed.tech/articles/fingerprint-trains-specialized-models-to-detect-distinct-fraud-types-128030.md>)

Original publisher: [Read original article](<https://www.helpnetsecurity.com/2026/11/11/fingerprint-fraud-score/>)

Author: Industry News

Published: 2026-11-11T09:12:57Z

Content type: release

Language: en

Sources: [Help Net Security](<https://devfeed.tech/sources/help-net-security.md>)

Topics: [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>), [online-fraud-prevention](<https://devfeed.tech/topics/online-fraud-prevention.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>)

Tags: [account-takeover](<https://devfeed.tech/tags/account-takeover.md>), [accounting](<https://devfeed.tech/tags/accounting.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [api](<https://devfeed.tech/tags/api.md>), [ato](<https://devfeed.tech/tags/ato.md>), [business](<https://devfeed.tech/tags/business.md>), [custom](<https://devfeed.tech/tags/custom.md>), [customer-data](<https://devfeed.tech/tags/customer-data.md>), [data](<https://devfeed.tech/tags/data.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [detection](<https://devfeed.tech/tags/detection.md>), [device-intelligence](<https://devfeed.tech/tags/device-intelligence.md>), [fake](<https://devfeed.tech/tags/fake.md>), [fingerprint](<https://devfeed.tech/tags/fingerprint.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [industry-news](<https://devfeed.tech/tags/industry-news.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [models](<https://devfeed.tech/tags/models.md>), [trains](<https://devfeed.tech/tags/trains.md>), [types](<https://devfeed.tech/tags/types.md>)

## AI overview

Fingerprint's Fraud Score trains and maintains separate fraud predictions using each organization's reported fraud outcomes together with Fingerprint device intelligence. It targets distinct threats--including payment fraud, account takeover, fake accounts, and promotion abuse--rather than applying one general risk score. Teams can use its predictions directly or integrate them through Fingerprint API responses; models are retrained as customers provide new outcomes. Fingerprint says this avoids the need for customers to build and maintain their own prediction models. In one head-to-head evaluation, it detected nearly 50% more fraud than one customer's in-house model without increasing the number of good users blocked; that result is specific to the reported evaluation.

## Source excerpt

Fingerprint has launched Fraud Score, a predictive fraud signal trained directly on customers' own fraud outcomes and powered by Fingerprint's device intelligence and machine learning models. Fraud Score learns the fraud types at each organization to help them identify fraud more accurately without having to build and maintain their own models. Basic risk scoring can't match the many types of fraud "Businesses today face a wider range of fraud threats, amplified by AI-powered techniques," said ... More -> The post Fingerprint trains specialized models to detect distinct fraud types appeared first on Help Net Security.