Machine learning models detect suspicious claims two weeks after submission, much faster than traditional methods, according to a new CLARA Analytics study on fraud detection in property/casualty insurance claims.
The research, completed in November 2024, analyzed 2,867 claims from 2020 to 2024 using an unsupervised machine learning approach.
The study found that nine percent of open claims were identified as high potential for special investigation unit referral.
Michigan and Arizona showed the highest percentages of potential fraud indicators.
The model’s predictions closely matched actual SIU referrals made by adjusters, but detected potential cases significantly earlier