Project Description

Claims Segmentation

The Claim Segmentation solution enabled one of the largest Insurance firms flag the fraudulent claims.

Customer’s Objective

One of the leading American insurance companies with more than 6,50,000 policy holders operates in a market where fraudulent activity can account for an estimated 6 to 10 % of all premiums. They wanted to improve its service to customers by settling claims faster and keeping premiums low. To achieve this, the company needed to maximize operational efficiency and find smarter ways to combat fraud. They worked with us to design a claims segmentation solution based on predictive analytics software.

Our Approach

Claim supervisor is the first person to notice the of loss information which is evaluated by assessing claim exposure and assigning the claim. Predictive modelling with traditional and non-traditional data elements from internal and external sources adds insight and perspective when evaluating the potential exposure of a claim. With predictive modelling, a more complete set of data can be automatically assimilated to accurately segment claims at the point of intake. And the enhanced segmentation is achieved by combining data sources available at various levels.

Business Impact

Predictive Modeling enhanced the insight at claim intake, promoting claim assignment consistent with exposure. Upon claim intake, the model instantly produces a score of 1 to 100 that indicates the future severity relative to an injury type.