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.

News & Commentary

11:45 AM
Nathan Golia
Nathan Golia
Commentary
Connect Directly
Facebook
Google+
LinkedIn
Twitter
RSS
E-Mail
50%
50%

3 Ways Insurers Can Win with Predictive Analytics

Implementation of predictive modeling is on a slow but steady climb in insurance. Here's some tips for getting the most out of your initiatives.

Implementation of predictive analytics capabilities has been on a steady rise in the insurance industry. There are implications for all lines of business in terms of how the technology can improve processes. But leveraging predictive modeling effectively means more than just implementing technology. Industry players share these tips for unlocking value from these efforts:

1. Bring in people who understand the readouts

Universal American, the health insurer who spoke to I&T yesterday about beating fraud with predictive analytics, completely remade its SIU in anticipation of the new approach. That didn't mean just bringing in technology folks, according to SIU manager James Cooper. Universal American brought in subject matter experts who could identify potential malfeasance in the data.

"We went from not a very sophisticated SIU to a full-blown unit that has nurses and coders and claims handlers," Cooper says. "Before it was just two handlers that were chasing down claims on a spreadsheet. We went from the stone ages to high tech in the matter of a year."

2. Impart the need for speed to IT

Models have traditionally taken a long time for IT organizations to create and deploy, according to Russ Schreiber, insurance industry principal for FICO, which partnered with Universal American on its predictive modeling initiative.

"The first challenge that we've seen is that a lot of carriers have all sorts of models, but they can't get them into a decision stream," Schreiber says. "The tech is solved, but the challenge is as much around culture. Once it's done, you shouldn't have to wait a year for it."

The velocity of "big data" demands a quicker turnaround as well, Schreiber adds.

"There's an awareness at the organizations that they've got this data and this knowledge," he explains. "And, it's much more readily available. It's much less this IT extraction initiative to get this data to the modeling teams. So people know they can get the data."

[See also: CIGNA's Mark Boxer opines on the potential for big data in insurance]

3. Don't discount public data

Towers Watson's recently released predictive modeling benchmarking study revealed that smaller insurers "face growing competitive pressure from large, resource-rich insurers" due to a perceived lack of data resources. But the consultancy says there are ways that companies of that size can "fast follow," including access to competitor filing materials.

FICO's Schreiber goes a step further, saying that no data set is complete without data from outside the organization.

"The ability to access the data has moved so far so fast, and it's internal as well as external sources," he says.

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