Fingerprint Launches Fraud Score, Reporting Nearly 50% More Fraud Detected in Customer Test

Fingerprint has launched Fraud Score, a predictive fraud signal that combines device intelligence with machine learning models trained on each customer’s own fraud outcomes. The company reports that the product caught nearly 50% more fraud than one customer’s existing in-house model in a head-to-head evaluation, without increasing the number of legitimate users blocked.

The launch addresses a familiar problem for risk teams: collecting signals is easier than turning them into a reliable decision. A device associated with several accounts might indicate promotion abuse, while an unfamiliar device attempting to enter an established account could warrant a different investigation. Fraud Score is designed to learn those distinctions from an organization’s actual users, traffic, and confirmed outcomes.

What the Reported Detection Gain Shows

Fingerprint’s headline result concerns a comparison with one customer’s internal model. The company says Fraud Score detected nearly 50% more fraud at the same level of legitimate-user blocking. That second condition is consequential: a system can catch more suspicious activity simply by rejecting more traffic, but doing so can also turn away genuine customers.

The result comes from a head-to-head comparison with one customer’s in-house model. It shows the value of learning from that business’s fraud patterns while keeping legitimate-user blocking steady.

The gain measures additional fraud detected. Its financial value depends on the transactions involved and how the business uses each prediction.

Separate Models for Different Fraud Problems

Fraud Score’s central design choice is to specialize predictions by fraud type. Fingerprint lists payment fraud, account takeover, multi-accounting, fake account creation, promotion abuse, platform abuse, and content abuse among its supported targets.

Those categories describe different behaviors and business costs. A payment-fraud model might help a merchant assess an order, while a promotion-abuse model could look for repeated attempts to claim an offer through multiple accounts. An account-takeover workflow has a different objective again: detecting unauthorized access without unnecessarily interrupting the legitimate account holder.

Customer outcomes supply the training feedback. Rather than asking every organization to build and operate its own prediction layer, Fingerprint handles model training and maintenance, combining its device signals with labels provided by the business. New outcomes feed subsequent retraining as the customer’s traffic and fraud patterns change.

This makes the quality of that feedback important. A model trained on confirmed outcomes has more useful supervision than one trained on an undifferentiated list of suspicious events. If an organization’s labels are incomplete or inconsistent, the resulting predictions can reflect those limitations.

Device Intelligence Supplies Context Beyond an Account

Fingerprint’s device intelligence platform combines persistent identification with contextual signals about web and mobile activity. Its role is to help businesses connect activity across sessions and inspect patterns that account details alone may not reveal.

The company’s Smart Signals catalog includes indicators for automation, browser tampering, virtual machines, proxies, VPNs, and unusually high device activity. These signals offer context for analysis; a privacy tool or unfamiliar environment does not by itself establish fraudulent intent.

Fraud Score adds a customer-trained prediction layer to that evidence. The distinction is between recognizing an environment and assessing how patterns in that environment relate to a particular business’s fraud outcomes. Teams can use the predictions directly or feed them into an existing decision system alongside their other information.

The approach also goes beyond blocking an identifier already associated with abuse. A trained model can look for combinations of signals associated with previous cases, potentially helping a business recognize similar behavior before the next transaction is completed.

A Feedback Loop Through the Dashboard, API, and S3

According to Fingerprint’s launch materials, customers can supply fraud outcomes through its dashboard, API, or S3. They can manage labels and analyze model performance, while predictions are delivered through Fingerprint’s API responses.

That architecture fits existing risk workflows. A decision engine can use the prediction alongside other checks to approve an interaction, request additional verification, or route it for review.

Continued retraining is intended to make the service responsive to evolving abuse. The feedback cycle still depends on what the organization learns after an event, including outcomes that may only become clear later. Monitoring model performance over time therefore remains part of operating the system.

Why Flink Wanted More Than Visitor-ID Blocking

The announcement includes an account from Flink, whose principal software engineer, David Fennessey, said blocking visitor IDs alone was insufficient against more sophisticated abuse. He described working with Fingerprint on a model informed by Flink’s internal fraud analysis to help stop future abuse before an order is placed.

Flink’s experience illustrates the collaboration behind the service: the business contributes its internal fraud analysis, and Fingerprint uses that feedback to build and maintain a model tailored to its abuse patterns.

Fraud Score moves the emphasis from maintaining individual signals and rules toward learning from a business’s own outcomes. Fingerprint handles training and retraining, while fraud teams retain control over how predictions inform their decisions. The product is available through Fingerprint’s Fraud Score page.