Fingerprint trains specialized models to detect distinct fraud types
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.
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.
said Suzanne Sando, Lead Analyst at Javelin Strategy & Research.
As customers provide new outcomes, Fingerprint continuously retrains the Fraud Score models.
However, account takeover (ATO), payment fraud, promotion abuse and fake account creation each exhibit distinct behavior, requiring distinct detection strategies.
We built Fraud Score to give every organization the power of custom machine learning without the complexity of building and maintaining custom models.
As online fraud becomes more sophisticated, security and risk teams struggle with translating more signals than ever before into accurate, actionable decisions.
Generic risk scores fail to capture these nuances, forcing engineering and fraud teams to spend countless hours on manual analysis, complex rule-building and ongoing model maintenance.
Fraud teams can act on Fraud Score’s specialized predictions directly or integrate them into their existing decisioning systems via Fingerprint’s API responses.
In a head-to-head evaluation, Fraud Score caught nearly 50% more fraud than one customer’s existing in-house model, with no increase in good users blocked.
What happened
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.
said Suzanne Sando, Lead Analyst at Javelin Strategy & Research.
What changed
As customers provide new outcomes, Fingerprint continuously retrains the Fraud Score models.
Who is affected
However, account takeover (ATO), payment fraud, promotion abuse and fake account creation each exhibit distinct behavior, requiring distinct detection strategies.
We built Fraud Score to give every organization the power of custom machine learning without the complexity of building and maintaining custom models.
Why it matters
As online fraud becomes more sophisticated, security and risk teams struggle with translating more signals than ever before into accurate, actionable decisions.
Generic risk scores fail to capture these nuances, forcing engineering and fraud teams to spend countless hours on manual analysis, complex rule-building and ongoing model maintenance.
Technical details
Fraud teams can act on Fraud Score’s specialized predictions directly or integrate them into their existing decisioning systems via Fingerprint’s API responses.
Response
In a head-to-head evaluation, Fraud Score caught nearly 50% more fraud than one customer’s existing in-house model, with no increase in good users blocked.