Claims Management by Computer: Analytical Data Mining and Claim Oversight is a Trend
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.
If the claims handling process were truly oriented toward efficiency and economy, an obvious place to look is the reflexive response calling for engineers and EUOs. Taking these costly steps without even bothering to look to see if a recent claim has any of the same characteristics of recently settled claims in the same association is obviously wasteful.
You'd think that after a carrier ends up settling a claim or two in a neighborhood, they'd look to see if other open claims on the same block, for homes built at the same time, might also share other similar characteristics. This is something that can be easily handled on the level of the File Examiner or Inside Adjuster.
Of course, the carrier would end up paying the claim sooner, rather than later, but the policyholder would be better served, and at less cost to carrier.
Gary,
Very good point. And, I do not think that all carriers have that claimms process because it is far too expensive.
QBE Insurance Company follows the process you discusss with many Condominium Association claims. The process is one of having the same contractors and enginneers go over the damage at the loss site. If the Association challenges anything, all the Association documents are requested and Examinations Under Oath scheduled.
This process leads to delay and frustration. QBE has been subject to wrongful claim practice lawsuits.
This is the type of stuff that's existed for years (i.e., Allstate's COLOSSUS program, CCPR, etc., et al). Corporate giants: can barely live with 'em and can't live without them (ha, ha). :)
SHIRLEY HEFLIN
I had some conversations, as a general contractor, with Jonathon Kost, of MS/B, a few years back. It was in regards to "junk" replacement cost estimates that were being thrown en masse into post-hail/wind storm business markets, by adjusters.
These adjusters were using the MS/B IntegriClaim construction estimating/"claim settlement" program. I may be mistaken, but I believe the construction estimating data incorporated into IntegriClaim was from Craftsman Publishing, or data like it.
Anyway, I also used IntegriClaim. I found out very quickly that insurers like Allstate Insurance, and their contracted adjusting firm, Pilot Claim Service, are intent on NOT estimating losses in a competitive construction market manner.
How so?
IntegriClaim, like any other similar general construction cost estimation programs, allows for historical and customary "Cost plus 10% (profit)" estimation methodology by a general contractor, or a contractor's estimator, in a given zip code region.
Among other things, IntegriClaim has instructions on how to account for (general contractor) labor, materials, sales tax, business overhead, and profit. MS/B even suggested (to insurers) when it was "appropriate" to account for GC O&P.
So, the individual line itemed costs can be modified...including leaving out of replacement costs altogether...general contractor overhead and profit factors.
So here I am, along with other contractors, putting out rational IntegriClaim estimates that account for inhouse production and subcontractor production, in a "cost plus 10%" manner.
However, Allstate would intentionally short a estimate by not accounting for, or applying, general contractor overhead and profit costs to roofing components costs.
They made claims then, that are similar to TWIA claims now, that stated:
'The "unit costs" contain contractor overhead and profit costs'.
What they actually meant though was that ROOFING contractor business overhead and profit costs was in the "unit costs".
(General contractor overhead and profit costs is a separate and distinct line item factored at the end of a MS/B IntegriClaim estimate).
So even though Allstate had charged for zip code replacement cost of a structure, and that replacement would likely require a general contractor, they try to discourage claimants from general contractor involvement costs on partial losses.
Besides trying to unfairly block me from my own market, Allstate market conduct led me to believe that insurers were collecting dollars from myself and others for general contractor replacement costs on structures in a given zip code, but then were controlling loss claim values (unfairly and unequitably) by not repaying losses based on actual general contractor structural cost values in the same zip code.
Long story short, Jonathon Kost explained to me that MS/B had no control over how Allstate (mis)uses their IntegriClaim program. To me, deep meaningful claim audits of insurers various "events" experiences can reveal how synthetic replacement costs are being perpetuated, and then hidden, by loss experience "analytics", via biased experts.
I also believe the "illegal windfall" that the Texas Department of Insurance Bulletin B0045-98 mentions has been openly reaped by many insurers in Texas, and has financially harmed the general public acordingly.
"Analytics" may actually be insurers dreaded data-mining witness against own their claim settlement practices...
____________________
This is an interesting note by Cunningham Lindsey, dated July 20th, 2005, and very similar to the Stuart Rose article - "Claims Analytics: Using Predictive Analytics to Optimize Your Claims Processes"
http://www.insurance-canada.ca/claims/announce/Cunningham-LIndsey-MSEB-507.php
By implementing Analytics, Cunningham Lindsey is sending a clear message that they want to understand the impact that their service and estimates have on their client companies’ book of business. This decision will allow them to demonstrate empirically the value that they bring to the table by proactively providing their granular performance metrics to their customers.
“The Claims Analytics process will help Cunningham Lindsey to quickly assess trends in adjuster behavior, identify out-of-pattern business practices, and implement best practices in addition to those that already make it one of the most successful players in the industry,” says Jonathan Kost, Vice President of Claims at MS/B.
Kost explains that MS/B Claims Analytics is a unique combination of expert people, systems, and strategy that interact within a company to bring significant, positive changes to their way of doing business. MS/B Analytics has gathered detailed property loss data and performed studies using enormous quantities of claims data.
“As a part of this engagement, Cunningham Lindsey will be supplied with information regarding how their estimates and service results compare to the independent adjuster market, as well as to the claims market as a whole.
This multi-faceted self analysis will allow Cunningham Lindsey to create a workforce of best-in-breed adjusters and to demonstrate the maximum amount of value in their service to their customers.” says Kost. “We can compare carriers to independent adjusting companies, a company to MS/B’s researched cost data, a carrier to other carriers, or even a carrier or company to itself.”
By using Claims Analytics a company can better assess how claims are handled and develop strategies to improve performance, reduce claims severity, and maintain fair settlement practices.
Cunningham Lindsey has decided to provide this service to all of their customers with the intent of creating parity between the performance created by a carrier’s own adjusting force and a Cunningham Lindsey adjuster. Further, Cunningham Lindsey will be engraining this dedication to quality.
In addition to implementing Claims Analytics services, Cunningham Lindsey is increasing the number of field adjusters using MS/B’s IntegriClaimTM property estimating tool and extending access to IntegriClaim AdministratorTM claims management technology to include all of its managers and supervisors.