Claims management and operational review for claims efficiency are truly sciences. The study and management of these are becoming increasingly computerized and intertwined with analytical data mining. I had dinner with a public and independent adjuster this week, where we discussed the process of litigation case handling and standards within my own law firm. As we were analyzing my operation, I kept imagining how much more difficult and complicated it would be to manage an insurance claims organization, and how computers were changing the claims organization.
The organizational claims directives and processes are significantly more complicated for insurers and independent adjusters than most realize unless you are at a management level within a claims organization. We make it a point at our firm to find and study these to understand why adjusters act the way they do and what the insurer’s motives are that drive the claims handling behavior.
Insurance and Technology had a recent article, Claims Analytics: Using Predictive Analytics to Optimize Your Claims Processes, which defined claims analytics as:
…the process to analyze the structured and unstructured data at all stages in the claims cycle (first notice of loss to payout to subrogation) to make the right decision, at the right time to the right party. Rather than analyzing one case at a time — based only on currently available information — analytics gives you added perspective by allowing you to view this one claim "in context" by comparing it with previous claims settlements in your database.
It seems common sense to use data and computers to be more efficient and accurate in any business process. I would be interested to see how the data is used and the actual results, given what the article indicated in part:
The power of claims analytics is that it works in conjunction with your existing claims management systems. Whenever claims data is entered or updated, analytics can be used to reevaluate the claim for loss reserve amount, fraud or subrogation opportunities. The ultimate strength of those evaluations, of course, lies in the amount and quality of available data.
…
Another challenge insurers facing today is the inability to accurately forecast loss reserves and ultimately predict outcomes once a claim has been submitted. Using analytics it is possible to calculate an accurate loss reserve amount and benchmark each claim based on similar characteristics and hence reduce the propensity for loss padding. For example, data mining techniques have helped insurers identify that the size of a claim payout grows significantly based on the number of days between when the claim occurs and when it’s reported. In most instances the size of a claim can increase by approximately 50 percent if the insured does not report the claim within the first four days.
Following up on this article, I found an excellent presentation on the topic at the 2009 Accord/Loma Envision Conference by Karen Pauli of the TowerGroup, an analytic advisor to insurance and financial companies. “Predictive Analytics for Claims Operations: Beyond Fraud” is an excellent update on why data should be considered as a means to more efficiently handle all claims and make the claims operation more efficient. While listening to her, I noted that Pauli made the following comment:
Claims is the one single point where the insurer and the customer come face to face.
She indicated that during the claims process, the insurance company has the opportunity to cement the relationship between the customer and the insurer. I would imagine that if it does not go well, claims can also sabotage the relationship and damage the reputation of the insurer. Depending on the motivation for data mining and how it is calibrated, I would suggest that computerized claims analytics can be used as a means to lower payments to less than full recovery.
Of particular concern is the concept of “claimant management.” I would suggest that this notion is to keep the claimant in a state of ignorance, so that the insurance adjuster and the insurance companies’ vendors are the sole source of information for restoration and settlement of the property insurance loss. Indeed, the “quick response” aspect of claims handling seems to be not only for the valid purpose of accomplishing prompt adjusting, but more importantly, to keep the policyholder from seeking different opinions regarding how the matter should be handled and gain greater benefits that otherwise would not be claimed due to ignorance.
We’ll see how the claims managers use the increasing trend of data mining as a tool to influence claims handling decisions. As with most things in life, tools can be used for ethical purposes or as devious methods of unethical conduct. If the claims managers and their analytical computer vendors are trying to quickly and efficiently provide the full benefit of the insurance product as promptly as possible to their customers through the use of claims analytics, they will not have to worry about criticism from policyholder advocates or regulators. Otherwise, I am going to be learning a lot about this new claims tool.
