Reducing Fraud with a Machine Learning Model and Ekata Identity Check

Success Story

Whitepages Premium created a logistic regression model that takes in a number of inputs such as payment behavior, information about the customer, and user behavior on the website, and then combines that data into a score.


Ekata provides businesses with global identity verification solutions via enterprise-scale APIs and web tools to help companies identify legitimate customers, prevent fraudulent transactions, and smooth new customer account creation. We developed our own fully-integrated, high-availability Identity Graph database that houses more than 5 billion global identity records. This real-time data integrates into existing platforms, authentication workflows, and data models to help businesses confidently assess and verify consumer identities worldwide.


Whitepages Premium, which provides access to U.S. public records to verify identities, was experiencing a high number of chargebacks due to new account fraud. Chargebacks needed to be at a manageable level. Otherwise, the company risked exceeding the 1% fraud rate which could result in the possibility of increased fines, or worst case, getting shut down by Visa or Mastercard.


Build a machine learning model for Whitepages Premium that scores transactions and identifies fraud. Leverage Ekata Identity Check Confidence Score to improve the effectiveness of the model.




Result #1

Model significantly reduced fraud and the number of chargebacks.


Result #2

Estimated that adding Identity Check Confidence Score to the model would save 12% per order.

Read the full story

Download the case study

Learn more

One of our experts will be happy to give you a free guided demo of Identity Check.