With decades of information in their databases, many insurers have started using those statistics to their advantage to intervene earlier in problem claims and to identify potential fraud.
With years of data to rely on, insurers have identified certain triggers that can indicate that a claim may require additional intervention and more hands-on management. The predictive modeling program will alert a claims adjuster when it identifies certain parameters or events.
This early identification of problem claims is helping employers and insurers achieve better outcomes for injured workers, as well as save money and time. As the trend continues, it should help reduce claims costs by eliminating more fraud and also lower the cost of some claims and reduce the time some injured employees are away from work recovering.
Conventional wisdom in workers’ comp is that 20% of the claims account for 80% of the losses. Efforts such as early claims reporting, medical case management and return to work have long proved essential for reducing claims.
Predictive modeling aims to improve the ability of insurers to identify claims that require early intervention.
Insurance predictive modeling applies statistical techniques and algorithms on insurance and claims data to develop variables that predict the likelihood of a particular situation (like a worker staying off work for longer than average).
While predictive modeling has been successful used for years by automobile insurers, it’s been slower to catch on in workers’ comp, particularly because it requires multiple data sets for which data availability can be scarce.
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.
In the case of a potentially fraudulent claim, some of these could include the number of prior injury claims submitted by a claimant and the amount of time that an allegedly injured claimant is out of work.
Employer tackles medical costs
Supermarket chain Ahold USA, a self-insured employer, started using predictive modeling in early 2012.
Ahold’s model uses claim characteristics, medical transaction details, and other data sources to identify factors that are predictive of higher claims costs.
Some of the indicators the company uses include multiple visits to doctors and the use of certain prescription drugs.
The model then prioritizes claims that need special handling and medical case management. This helps injured employees receive appropriate medical care to reach maximum medical improvement and return to work sooner.
The company’s predictive modeling can indicate whether a claim has the propensity to develop adversely. It can also 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.
The results for Ahold have been positive, resulting in a lower workers’ comp expenditures in “low seven digits.”
Insurer birddogs fraud faster
National insurance company Chubb Corp. has been using predictive modeling for both its workers’ comp and automobile claims.
At Chubb, 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 and patterns that the claims adjuster may not detect.
If a claim is flagged, the adjuster can investigate further and/or monitor the claim. If certain warning signs appear, the claim is referred to Chubb’s insurer’s special investigation unit. At that point the SIU can work with the claims adjuster to investigate further.
Before predictive modeling at Chubb, it could take up to 180 days to spot potentially fraudulent workers’ comp claims and assign them to the SIU. Now that number is down to six days.
Also, predictive modeling has led to a significant increase in accepted referrals to the insurer’s SIU. As a result, the number of investigation days has decreased, and the company has achieved significant cost savings.