Success Case | Potential Fraud Detection in Claims
Large European Insurer
Quick view
The Challenge
The organization has a limited team of data analysts who work with rules systems to identify potential fraud situations in the processing of household claims. The team is limited and the volume of open files exceeds 1,000 per day.
The Solution
Keepler has developed a data product for the identification of potential fraud in files, supported by machine learning. It combines a set of more than 300 variables from internal and external sources, with unstructured data from claims reporting. In addition, in the daily prediction, the variables and their values that make that file identifiable as potential fraud are singled out on a file-by-file level.
To ensure customer satisfaction and brand image, the system must be sensitive enough to avoid false positives, so Keepler develops several models in order to select the one whose behavior provides the highest accuracy.
The Result
Keepler is a full-stack analytics services company specialized in the design, construction, deployment and operation of advanced public cloud analytics custom-made solutions. We bring to the market the Data Product concept, which is a fully automated, public cloud services-based, tailored software that adds advanced analytics, data engineering, massive data processing, and monitoring features. In addition, we help our customers transition to using public cloud services securely and improve data governance to make the organization more data-centric.
Would you like to talk about your business?
We can help you leverage the power of data to enhance your operations.