It's no secret that high premium rates for workers' compensation insurance are pressuring both insurers and employers. Nationwide, medical costs are skyrocketing despite a decline in the number of claims filed for workers' compensation. In a 2004 study by the National Council on Compensation Insurance, the medical share of total benefit costs in workers' comp rose to approximately 55 percent on a countrywide basis, with some individual state shares approaching 70 percent.
According to the National Insurance Crime Bureau, workers' comp fraud costs Americans more than $5 billion nationally and accounts for at least 10 percent of the cost of workers' comp premiums. Workers' comp fraud and abuse hurts employers because higher insurance premiums can dramatically increase their cost of doing business.
Claimant fraud comes in many guises. Some workers fake injuries at the workplace to get paid for staying home. Some exaggerate the extent of injury to prolong time away from work, while others claim their injuries occurred at work, when, in fact, they happened off premises and are unrelated to work.
Workers' comp fraud and abuse is hard to detect because a significant amount of claims start off as legitimate. The longer it takes to discover a fraudulent claim, the more money is paid out. That's why early detection of fraudulent and abusive claims is critical to containing the cost of workers' comp. And the more insurers can decrease their losses, the more likely it is that their insurance rates will be lower as well.
Claims departments are typically the first line of defense in detecting fraud. But manual detection processes used by many claims departments allow most fraud to slip by undetected. Industrywide, adjusters handle an average of 250 claims at any given time.
Even the best claims adjuster can't perform the detailed analysis needed to find complex patterns that indicate fraud.
The Coalition Against Insurance Fraud estimated that 20 percent of the total fraud at most is detected, and much of this fraud is detected late in the life of the claim. In addition, a high percentage of claims that are referred to special investigative units often are not fraudulent leads. The time and cost to investigators to pursue suspicious claims that don't turn out to be fraudulent or abusive contribute to the high cost of workers' comp. Until recently, however, no tools existed to improve the quality and quantity of cases referred for review.
But what if it were possible to substantially reduce the amount of time adjusters spend on claims while increasing accuracy and quality? What if adjusters could analyze claims faster and more thoroughly, making better decisions early in the life cycle of the claims, before losses begin to mount?
A POWERFUL TOOL
The good news is that we can. Today, the insurance industry has a powerful tool available to fight workers' comp fraud and abuse: predictive analytics.
Predictive analytics software models based on neural network models, an advanced form of artificial intelligence, can enable insurers to identify fraudulent, abusive and high risk claims much earlier and with a higher degree of accuracy than any other known method, while swiftly and accurately processing the majority of claims without adjuster intervention.
Predictive models are largely responsible for the dramatic turnabout in the credit card industry. Today, predictive models are used to screen 85 percent of U.S. credit card transactions for fraud, resulting in a 50 percent reduction in industry losses. This same technology used so successfully by 65 percent of the world's credit card issuers is now increasingly being deployed to contain the spiraling costs of workers' comp.
Predictive models are highly effective because they are capable of analyzing thousands of data elements simultaneously to find subtle, complex and hidden patterns of suspicious behavior. Their analytical and processing strength enables high-volume claims departments to perform a rigorous, objective review of every claim. While human experts are capable of identifying some red flags and simple fraud patterns, sophisticated modeling techniques are required to find more complex patterns of fraud. Based on historical examples already determined to be fraud and abuse claims, neural network predictive models can learn which subtle patterns are associated with a high likelihood of fraud and which are not.
Predictive models are accurate because the technology recognizes patterns from the data itself, not from pre-existing assumptions on what the data means. As a result, the system provides high-quality referrals to investigative units, further reducing losses. In addition, neural networks also are the only systems sophisticated enough to detect fraud types that have not been seen before. Claims are reanalyzed frequently for new aberrant activity.
Only a small percentage of claims account for the majority of claims costs. These more costly cases include both legitimate claims that for various reasons require special handling. Predictive analytics can help insurers identify these high risk claims rapidly, allowing these exceptions to be routed to experienced case managers or investigative units, freeing adjusters to process the remaining claims with no outside resources.
The trick is separating these high-risk claims from the rest. Many fraudulent or abusive claims don't look all that remarkable at first, even to the eye of a well-trained adjuster. Clues may be subtle and submerged in an ocean of data. In the case of a bodily injury claim, for example, medical factors indicating a need for special handling may become evident only after some amount of treatment. In the case of fraud, opportunists who initially file legitimate claims may eventually fall prey to the temptation to exaggerate or misrepresent their cases. In fact, the majority of insurance fraud starts out this way.
Another factor contributing to high claims costs is that present methods are skewed toward apprehending fraud rather than identifying other types of high-risk claims. Predictive analytics are highly effective at reducing claims costs because they are extremely effective at identifying these high-risk exception claims, both legitimate and fraudulent. By accurately culling out high-risk claims, predictive analytics can make it practical and safe for insurers to process and close a vast majority of claims faster. Insurers save money by identifying suspicious and high-risk claims at the earliest possible moment, enabling preemptive action to be taken to prevent losses from occurring.
In a fraction of a second, the predictive models can consider thousands of variables simultaneously, looking at complex relationships between data and deciphering subtle clues and slight nuances that may remain hidden to even the most seasoned adjuster.
These advanced methods are applied not only to the initial claim documents, but also to every transaction associated with the claim over its entire life cycle. Each new Workpiece of data coming in is analyzed thoroughly against not only the claim history, but a vast database captured from industry claims.
Predictive analytics are accurate because they are objective. The software learns to recognize patterns from the data itself, not assumptions about it. This pattern recognition capability is dynamic; when the data indicates something new, the software updates its detection criteria.
In comparison tests, 55 percent of claims were identified weeks or months before they were discovered manually, and the software often discovered suspicious claims or claims needing case management that would have been missed by insurance claims analysts. Overall, insurers using predictive analytics software technology to detect fraudulent and abusive claims have experienced a return on investment of 20-to-1, or up to $300 per claim in savings.
The insurance industry is undergoing a momentous change. Like the credit card industry in the 1990s, the insurance industry is about to realize that losses and administrative expenses it previously accepted as a normal cost of doing business can, in fact, be substantially reduced.
In a time when workers' comp costs have become not just an insurance industry issue, but a major business and political issue, the use of predictive analytics to identify fraud, abuse and high-risk claims early has the potential to revolutionize property and casualty insurance.
KEVIN LISLE is product manager of property and casualty analytics at Fair Isaac Corp., in Minneapolis.
November 1, 2005
Copyright 2005© LRP Publications