Bayes Fraud

Create a vendor selection project
Click to express your interest in this report
Indication of coverage against your requirements
A subscription is required to activate this feature. Contact us for more info.
Celent have reviewed this profile and believe it to be accurate.
We are waiting for the vendor to publish their solution profile. Contact us or request the RFX.
Projects allow you to export Registered Vendor details and survey responses for analysis outside of Marsh CND. Please refer to the Marsh CND User Guide for detailed instructions.
Download Registered Vendor Survey responses as PDF
Contact vendor directly with specific questions (ie. pricing, capacity, etc)


BayesFraud is a market-leading predictive analytics solution that provides insurers with advanced, automated fraud detection capabilities during claims handling.

Our solution consistently evaluates all submitted claims for fraud and alerts claims handlers to high-risk claims. In this way routine claims can be fast-tracked for immediate settlement, and claims with the highest likelihood of fraud can be investigated further – before costly claims are paid out.

The results: A positive end-to-end claims experience strengthens customer loyalty and retention. And when only high-risk claims are sent to investigators, hit-rate accuracy increases and valuable time and resources can be dedicated to claims with the greatest potential of fraud – and cost savings for insurers.

Key Features

The following table list the features and function the solution support and how it is supported around:

·Data preparation

·Model configuration

·Claims fraud techniques

·Special Unit Investigation (SIU)

Key Benefits

  • It combines claims data with the incredibly valuable input from claims and fraud experts in one and the same model

  • It quantifies missing and uncertain data and observations, to “fill in the data holes” in claims data Calculates fraud on the basis of every shred of evidence available

  • Uncovers insight about fraud patterns and relationships that would otherwise be missed using manual or rules-based processes

  • Learns from data as more claims data and information become available

Product/Service details