A rather typical business story became a head-scratcher of a Workers’ Comp claim — and an illustration of the power of predictive modeling — when a seemingly “normal” claim was flagged for potential fraud.
A person traveling for business stayed in a hotel, as many people do when they travel, but with a twist. He filed a Workers’ Compensation claim for supposedly suffering an injury after falling off a chair in his room. According to the claimant, he could no longer work, but he didn't expect that a predictive modeling tool would flag his case based on his occupation and other factors, bringing it to the attention of the insurer's Special Investigations Unit (SIU).
After a little digging, an SIU investigator found that the claimant had not reported the incident to the hotel and did not have any doctor bills. And when the investigator interviewed the claimant at his home, he spotted a broken chair on the outside patio. The claimant noticed that the investigator saw the chair, and immediately told the investigator that he wanted to withdraw the claim. Although there was no apparent reason for the claimant's reaction, the investigator suspected that the claimant may have injured himself falling off this chair at home, not a chair at the hotel.
This real example demonstrates how predictive modeling empowers a claims staff to be better, faster and smarter when it comes to fraud detection, particularly for Workers’ Compensation and auto bodily injury claims. Although it can be a balancing act to identify potentially fraudulent claims and still provide superior customer service for justified claims, a handful of factors can ensure success. They include the increasing speed with which predictive modeling allows claims teams to act, the ability to identify potentially fraudulent cases throughout the claims process, maintaining and enabling the human element in claims adjusting, and strengthening an insurer's anti-fraud reputation.
Speeding it up from start to finish
Before predictive modeling at Chubb, it could take up to 180 days to spot potentially fraudulent Workers’ Compensation claims and assign them to the SIU. Now that number is down to six days. For auto bodily injury claims, four months was the average time required for an SIU referral; today, it is only four days.
The greater efficiency has resulted in significant savings. Predictive modeling has led to a significant increase in accepted referrals to the SIU for both Workers’ Compensation and auto bodily injury. As a result, the number of investigation days has decreased, and the company has achieved significant cost savings.
How is this possible? Quite simply, speed is crucial for investigating a claim. Evidence is still fresh. Claimants’ and witnesses’ memories are still vivid. Additionally, reacting to a claim quickly can serve as a deterrent to fraudsters who are “on the fence,” as it did with the claimant with the broken chair. And companies know that the longer it takes to settle a liability claim, the more likely the claim will be litigated.
Speed is also critical to delivering excellent customer service. By quickly identifying potentially fraudulent claims, the company is able to be more efficient and spend more time on customers who have valid claims.
Although predictive modeling can identify a potentially fraudulent claim faster than many cases in the past, successful claims adjusting operations continue to monitor claims as they progress and flag them later if certain warning signs appear.
Predictive modeling begins with the first notice of loss and then continues to monitor for certain trigger points and specific actions during a claim's lifecycle, such as the number of prior injury claims submitted by a claimant and the amount of time that an allegedly injured claimant is out of work. The model flags claims based on patterns that have historically proven fraudulent — patterns that a human adjuster often may not detect.
In addition to detecting fraud, predictive modeling can indicate whether a legitimate claim has the propensity to develop adversely. It can be used to evaluate the likelihood that a claim will result in litigation. It may also provide the ability to identify Workers’ Compensation claims with a greater likelihood of surgery. Such tools allow adjusters to develop case strategies at first notice and gain control over the claim as it progresses.
Smarter allocation of resources
Despite the wealth of benefits from predictive modeling, the machines are not taking over. Adjusters are still the critical element in claims management and fraud detection.
The “tool” delivers information that gets adjusters thinking about fraud and looking for clues. Modeling does not prove that a claim is fraudulent; it tells adjusters to look closer. After that, they must still conduct their claim investigation. For instance, when predictive modeling registers a claim as highly suspicious, a notice is forwarded to the SIU, where investigators triage the claim and determine whether it should be accepted. Once the SIU accepts the claim, the SIU and file handler plan the investigation together, with the claims handler maintaining ownership over the adjustment process.
When done well, predictive analytics does more than just inform; it smooths out the efforts of hundreds of adjusters across multiple claims offices around the country. In any given group of adjusters, some will be more focused on detecting fraud than others. Predictive modeling builds a ground-floor foundation of awareness so that these differences are minimized.
Human beings also have a say in how the modeling tools are developed, integrated and used. The Chubb Claim Analytics team seeks input from claims professionals and gathers their feedback to analyze business benefits and to discover ways to improve existing solutions and create new ones.
Better reputation management
Most important, predictive modeling can help create a deterrent to fraud. Police and other authorities know that fraud perpetrators talk to each other. They share information on insurance companies, down to particular claims offices and individual adjusters who are easy “marks.” Predictive modeling can help insurers send the message that their company's claims organization is not an easy target for fraud.
At present, predictive modeling is showing clear signs of success — increased speed, smarter human involvement, financial savings, better reputation management and continued vigilance. As the technology is further developed, it will become better integrated into the claims process. While many claims today are still handled manually and in the order they are received, predictive modeling will help insurers move even more toward segmentation. The tools will enable SIUs to identify those claims that are best suited for experienced staff at a given office, for instance, or those severe enough to require immediate review, contact and intervention.
Moving forward, greater success will also involve the ability to input additional unstructured data into the modeling systems. Posts on social media, such as those linking a claimant to known fraudsters, are examples of information the company hopes to stream into the systems. Though the use of such data can be sensitive because it may contain personally identifiable information, it may be possible for firms to navigate safely around the potential privacy issues. In the near future, systems will be able to track and match social media with claims data.
It will be a new age of enhanced claims management and customer service. But it still will be a world in which it will be important for an adjuster to spot that broken chair.
We’re on Facebook, are you?