South African general insurer Santam — last seen punking a fast-food restaurant with a viral television commercial — says that it has saved $2.4 million on fraudulent claims using IBM analytics.
Santam's claims division developed a new operating model for processing claims, depending on varying risk levels. The IBM offering helps assess any fraud risk associated with incoming claims and allows the insurer to distribute claims to the appropriate processing channel for immediate settlement or further investigation. Santam is also able to reduce the number of claims requiring an adjuster, helping reduce average claim cycle time from three days to about an hour.
"The scoring process is based primarily on sets of predefined business rules – but as we process more claims and get more data in the system, we will be able to build more complex predictive models," says Anesh Govender, head of Finance, Reporting and Salvage at Santam, in an e-mail to Insurance & Technology. "We’re particularly interested in building propensity models to look at customer behavior. This would enable us to group customers into different risk profiles, so that we can segment our best customers and offer them more tailored products and higher service levels."
Santam is also looking at more general risk factors related to claims, including catastrophe propensity of a region.
"Based on existing claims data, we already knew that statistically most car accidents occur around 10am, but that most fraudulent ‘accidents’ happen between 10pm and 5am," Govender adds. "So the time that the accident is reported is a key factor in determining the risk score of the claim."