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

02:59 PM
Russ Schreiber, VP of the insurance practice at FICO
Russ Schreiber, VP of the insurance practice at FICO

The Fight Intensifies Against Health Care Insurance Fraud

Too many insurers still accept fraud as a cost of doing business, or seek to curtail it using a set of rigid rules. Common sense tells us that it’s much more effective to stop fraudulent payments before they are made than to chase the money after the fact.

Editor's note: This is part one of two in a series.

Industry estimates indicate that erroneous, abusive and fraudulent claims are costing the health care industry hundreds of billions of dollars each year. In the United States alone, the Center for Medicare and Medicaid Services estimates the numbers to be anywhere from $200 billion to $600 billion a year, and federal agencies reported that in 2010 Medicare fraudulent claims represented nearly 40 percent of all government waste.

The fight against health care insurance fraud is now on. Without solving this problem, it will be nearly impossible to bring health care expenditures under control and equally difficult to make Medicare solvent over the long haul. Fortunately, we can take a large bite out of insurance fraud with smarter predictive analytics that uncover more fraud than current technologies detect, and find fraud earlier in the claims lifecycle.

The Problem

Currently, the U.S. health care system is not in a position to claim the upper hand in the fight against insurance fraud. The principal reason for this is the reliance on technologies and methodologies that are less advanced than those used in other industries, such as the credit card industry, to prevent fraud.

Too many insurers still accept fraud as a cost of doing business, or seek to curtail it using a set of rigid rules. Most insurance providers also continue to utilize a post-payment correction model, despite the obvious advantages of stopping fraud before any payments are made. Common sense tells us that it’s much more effective to stop fraudulent payments before they are made than to chase the money after the fact.

New Tools for Fraud Detection Now is the time to evaluate the benefits of using more advanced predictive analytics tools to prevent mounting losses. As the complexity and scope of insurance fraud grows, the systems used to detect and prevent fraud, waste and abuse need to evolve as rapidly as the patterns of misuse that insurance providers are trying to identify.

This ability to quickly evolve is essential for catching and eliminating emerging fraud threats. For companies and agencies looking to ensure payment integrity, proactive solutions are needed to identify and address problems before they occur, cutting off fraudulent activities at the source.

When it comes to technology, the most common solution today to detect fraud, waste and abuse is business rules. Rules-based detection is effective, but rules by their very nature can only be written to catch suspicious activity based on known information. This leaves the door wide open for emerging threats that capitalize on the fact that rules-based systems cannot proactively search for what they do not know.

For example, many insurers have a rule that a claim filed less than 30 days after a policy is written should be flagged and investigated. This seems sensible enough, but in reality it is precisely the kind of rule that sophisticated criminals will anticipate and outsmart. In fact, FICO has seen evidence of policy holders that will pay the first couple of premiums and avoid claims for a period in order to masquerade as a “good” account before making a significant claim to maximize the fraud.

At the same time, abnormal patterns can go undetected. In one case, a provider ordered repeated hearing tests on children, walking away with $3.5 million in excess charges over the course of five years. Rules-based detection has a difficult time flagging this action; how would a rule be written to not exclude tests for children who legitimately require multiple hearing tests? Yet claims that seem legitimate in isolation may actually be part of a larger pattern of fraudulent activity.

Predicting Human Behavior

Predictive analytics is based on the principal that human behavior is inherently predictable. Analytic technology can essentially flag claims such as those in the example of the hearing tests as unusual or aberrant compared to “normal” behavior, forwarding them to analysts for additional review, highlighting a systematic pattern of abuse and catching an expensive problem long before rules-based claims analysis identifies it as an issue. This allows unusual or problematic claims to be flagged and reviewed before the abuse becomes widespread.

Using complex, multidimensional analysis, claims are assigned a score that can direct analysts to only the most aberrant claims and providers. The score is accompanied by one or more explanations, highlighting the reasons why the claim or provider appears to be suspicious. Analysts can use this information to quickly determine whether a claim is legitimate, fraudulent or worthy of further investigation.

Used in pre-payment situations, predictive analytics can identify problems like adjudication errors, upcoding, OCR scanning issues, unit inflation and payment policy weaknesses, thereby decreasing the volume of payments made on fraudulent, erroneous or abusive claims. Most claims can be analyzed in minutes if not seconds, ensuring that there are no processing delays that would risk problems with prompt payment legislation. This gives insurance providers the ability to avoid the “pay-and-chase” models that have been ineffective all these years.

The system can also address post-payment analysis, examining large sets of data – often several terabytes of data – in complex, nonlinear ways to identify aberrant patterns in patients, providers or procedures that aren’t evident in smaller batches. This increases detection accuracy while improving investigator productivity and recovery success. Plus, advanced analytic systems can substantially reduce the rate of “false positives,” minimizing the number of legitimate claims referred for investigation.

The next installment will discuss combining predictive analytics and rules to produce a stronger fraud-fighting organization.

Russ Schreiber is vice president of the insurance practice at FICO. For more information on FICO’s predictive analytics combating insurance fraud, waste and abuse, visit

Register for Insurance & Technology Newsletters