IBM's Analytics Gives Instant Investigation Functionality

SOMERS, NY, November 17 -- IBM announced today that it is putting advanced analytics to work zeroing in on fraudulent and abusive claims in the Property & Casualty (P&C) Insurance industry. The IBM Loss Analysis and Warning Solution is designed to help protect P&C insurance companies from illegal, unethical, or undesirable activities by policyholders, service providers and employees. This is accomplished through a combination of data mining technology, data visualization techniques and a powerful scoring and anomaly discovery engine.

According to the National Insurance Crime Bureau, at least 10 percent of all insurance claims are either inflated or outright fraudulent, leaving the industry to pay out as much as US$30 billion annually in fraudulent claims.

Recognizing the ultimate impact this fraud and abuse has on business and consumers, IBM designed the Loss Analysis and Warning Solution to identify fraudulent and undesirable behavior and provide data analysis capabilities for the P&C insurance industry.

This information can be used by insurance companies to detect a variety of unusual or suspicious behaviors such as inflated or unnecessary payouts to claimants, misuse by agents of policy discounts and detection of unusual claims charges and billing practices from service providers such as repair shops, doctors and hospitals.

With the new IBM Loss Analysis and Warning Solution, P&C insurance investigators create compliance models for claims, individuals and organizations expected to display similar behavior. The solution identifies normal behavior in these ‘peer’ groups and makes comparisons to rank and score members and identify unusual behavior. For example it would flag an auto repair shop that was charging for towing on nearly all repairs, while other shops had towing charges less than 20 percent of the time.

The Loss Analysis and Warning Solution can also be configured to immediately analyze a claim as it is filed as part of the claim review process. This helps insurance companies to avoid the “pay and chase” dilemma, where the claimant suspected of fraud is pursued and investigated long after the claim is paid.

Additionally the solution offers an automated capability that acts as an “investigator-in-a-box.” Rather than having the investigators develop the analysis parameters, this feature automatically applies analysis modules and logic to the data to identify questionable behavior, which can significantly increase productivity by freeing up the investigators to focus on case development and pursuit.

The new solution can be licensed for direct analysis or as an on-demand solution hosted by IBM at an IBM facility. It is based on the same technology as IBM's Fraud and Abuse Management System, developed over the last decade by IBM researchers and consultants in collaboration with health care insurance firms to detect fraud, waste and abuse in the health care industry.

The IBM Loss Analysis Warning Solution is available today through the IBM Center for Business Optimization. This group is putting advanced analytics to work by tapping into IBM's deep computing skills, industry consulting expertise and IBM Research's mathematical modeling capabilities to develop solutions that tackle complex problems involving massive data sets. In addition to risk management optimization, the Center offers solutions in the areas of supply chain management optimization, marketing investment optimization and dynamic pricing optimization. The Center is part of IBM Global Business Services. For more information, visit