Insurance & Technology is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Security

05:25 PM
Connect Directly
Facebook
Google+
LinkedIn
Twitter
RSS
E-Mail
50%
50%

Carriers Should Apply Predictive Modeling Earlier in the Claims Process: Deloitte

By using predictive analytics early and often, insurers can identify potentially severe or fraudulent claims.

Advances in predictive analytics allow insurance carriers to use data acquired at first notice of loss to segment claims by severity, Deloitte (New York) says in its latest report, Driving Operational Excellence in Claims Management.

"Predictive modeling has become table stakes on the underwriting side because it's a revenue generating area," Deloitte principal Pil Chung says. "Now carriers are starting to look at the other side of the equation, which is cost management."

It's important for insurers to identify potentially complex claims early because 20% of claims drive 80% of losses, Deloitte says in its report. The company asserts that effective use of predictive modeling early in the process can drive a four to eight percent reduction in annual loss and expense; a three to seven percent improvement in nurse-managed claims; a five to 10 percent improvement in claims managed by a fraud investigator and a 20 to 25 percent redeployment of supervisory resources.

"Traditionally, you wait until the claim develops, to see a pattern," Chung says. "But now, with predictive models, we're getting that insight way up front."

It's not as simple as a one-and-done approach, Chung says. Predictive models should be applied early and often through the life cycle of a claim, as new data are introduced. And, if an event such as a catastrophe occurs, these analytics can help establish which claims can be automated, and limited resources can be most effectively deployed to the toughest cases.

"When you start to realize that the claims are on the rise in total, having models that can detect certain things, good or bad you can try to automate those," he explains. "When you're expecting more claims coming through the door, having these tools to help you helps you balance your workload better."

An advantage to predictive analytics is that those capabilities can be implemented without required a wide tear-down of legacy claims systems, Chung adds. Insurers should look to add other capabilities that are likewise uncomplicated, such as business process management.

"I think we have to get away from the notion of having to gut and replace everything. The tools allow you to work around those legacy systems," Chung says. "You now have tools and rules engines that sit on top allowing you to do routing of work and monitoring of work much easier. It's one of the biggest advancements that we see claims organizations implement."

Nathan Golia is senior editor of Insurance & Technology. He joined the publication in 2010 as associate editor and covers all aspects of the nexus between insurance and information technology, including mobility, distribution, core systems, customer interaction, and risk ... View Full Bio

Register for Insurance & Technology Newsletters
Slideshows
Video