Infinity Property & Casualty: Staking the claims process on predictive analytics

Smarter Planet Leadership Series Video

Published on 05-May-2011

Validated on 13 Dec 2013

Customer:
Infinity Property & Casualty

Industry:
Insurance

Deployment country:
United States

Solution:
Database Management, Big Data, Big Data & Analytics, BA - Business Analytics, Business Performance Transformation, Customer Relationship Management, BA - Predictive Analytics, Smarter Planet

Smarter Planet:
Leadership Series, Smarter Insurance

Spotlight

While Bill Dibble doesn’t believe in “silver bullets,” he saw predictive analytics as something that could be used to help Infinity address a number of challenges and opportunities. While his area is Claims Operations, he articulated an expansive, enterprise-wide vision for the company and is leading the charge to make it a reality.

How Accomplished:
Good ideas usually start simple— and Dibble’s idea was. His insight was to “score” claims like lenders score credit, to provide a more systematic, efficient and accurate way to pinpoint fraud. But that was just the beginning. His breakthrough was to leverage the same underlying intelligence to create a smarter claims processing workflow. That made it possible to transform the way Infinity’s agents handle and route claims, resulting in a lesser reliance on external adjusters, lower adjustment costs and—because claims are handled faster—more satisfied customers.

Leadership:
Leaderhip is...Big picture thinking Bill Dibble pursued predictive analytics to address what he saw as a growing fraud problem as well as the company’s overall goal of achieving a world-class claims capability. However, in framing and then championing his vision, he took an enterprise view— looking at how it could be used across the company as a whole. “As soon as [Dibble] wrapped his mind around it, he became a visionary and an evangelist for predictive analytics—not just for claims—but also for pushing its value across the enterprise.” — Eric Eckert, IBM Business Analytics

Lessons Learned:
Believing the intelligence. Infinity’s case shows that topdown support isn’t enough to make predictive analytics a success. Dibble’s line managers and regional claim managers were instinctively skeptical of something they didn’t necessarily understand. He sees it as a communications challenge. “For predictive analytics to be effective, consumers of the intelligence have to believe the results.” — Bill Dibble, SVP of Claims Operations, Infinity Property & Casualty

Benefits:
400% ROI with six months of implementation; Increase of $12 million in subrogation recoveries; As much as 95% reduction in time required to refer questionable claims for investigation; Increase in success rate in pursuing fraudulent claims from 50% to 88%; Ability to keep 25% of claims within the company’s first notice of loss area (up from 4%), enabling Infinity to sharply improve its Loss Adjustment Expenses (LAE) ratio

Video

Good ideas usually start simple— and Dibble's idea was. His insight was to "score" claims like lenders score credit, to provide a more systematic, efficient and accurate way to pinpoint fraud. But that was just the beginning. His breakthrough was to leverage the same underlying intelligence to create a smarter claims processing workflow. That made it possible to transform the way Infinity's agents handle and route claims, resulting in a lesser reliance on external adjusters, lower adjustment costs and—because claims are handled faster—more satisfied customers.




Video Transcript


IBM Leadership Series Customer Reference

Infinity Insurance Company
Interviewee: Bill Dibble – Senior Vice President, National Claims, Infinity

TEXT: Smart is…combating insurance fraud with data
Infinity Insurance Company writes over $1 billion in automobile insurance
Issuing a majority of their policies in predominantly metropolitan areas
And processing more than 25,000 claims every single month

Bill Dibble: Fraud is a huge problem for insurance companies. The National Insurance Crime Bureau predicts that it’s a 20 billion dollar risk to the insurance companies each year.

We wanted to speed the process of those claims that did not have fraud involved. We want to treat that customer who has everything going right, paying what he’s owed and getting him back on his feet in as quick a manner as we can. So we presented our ideas to our executive board. I think what really inspired them was the solution that we were going to improve the customer experience.

Certain data is captured by the first notice of loss adjuster into a loss report.

And that’s thousands of records. Through the text mining that data is used to develop rules to formulate whether that claim should be moved to a field adjuster who needs to go out in the field, investigate and make a determination as to liability and to damages.

The rules are affecting the actual reports by giving you the analytical data that’s necessary to carry on with the day to day business.

We assign to each of these rules a point value and based upon the higher the point value, the probability of this claim has to then be pushed to a special investigator becomes very high.

Or if the point value was low, we would fast track that claim.

We went from identifying fraudulent claims that would take us 14 days down to 24 hours

After three months, recognizing 403% return on our investment, many eyes were opened and in a company that is handling millions of dollars in payments each month, that’s a tremendous sum of money. It’s like looking in your pocket and finding a million dollar bill.

The IBM SPSS product has only begun to scratch the surface of what it can do for auto claims. It’s reduced fraud, it’s made a much quicker turnaround time for specialists to become involved in claims, it’s increased our subrogation dollars.

By being a smarter insurance company, we’ve become a much more competitive insurance
company to our customer. We’re doing new things, we’re predicting the future for individuals.

Text: The Infinity Insurance Company solution is based on:
Software:
IBM SPSS
IBM Cognos

Products and services used

IBM products and services that were used in this case study.

Software:
SPSS Modeler, SPSS Risk Control Builder, SPSS Decision Management, SPSS Collaboration and Deployment Services