Over the past decade, the use of predictive modeling in commercial lines has gone from a powerful tool leveraged by a few strategic early adopters, to table stakes for most insurance companies. The industry has seen a tremendous evolution in the use of advanced analytics and predictive models in the underwriting process. On the claim predictive modeling side, we appear to be moving rapidly out of the early adopter stage, partially because of the advent of Software as a Service (SaaS) and cloud computing.
Unlike the early days of underwriting predictive models, claim predictive models can now leverage the cloud as a way of bringing analytics to life faster for insurance companies and self-insured entities that don't have the large scale or resources of some bigger companies. As a result of the changes in technology, many claim organizations are wrestling with the "how" and "when" elements of the deployment equation, versus the historical "if" side.
The Evolution of Claim Predictive Modeling
Deloitte Consulting LLP has been engaged with the development of advanced analytics capabilities for more than 15 years, beginning with insurance underwriting, and moving on to claim management in 2006. Deloitte's advanced analytics efforts in claims started with the workers' compensation line of business, developing separate first notice of loss (FNOL) models and subsequent monthly models for lost time indemnity, lost time medical, and medical only claims.
The firm's claim modeling then expanded to personal lines bodily injury, commercial auto bodily injury, and general liability. For each of these lines, there are a variety of ways to turn modeling insights into actionable business results. For example, use business rules to drive resource allocation based on factors such as the potential claim severity and duration, propensity for fraud or litigation, subrogation opportunity, or other business applications.
Similar to the early adopters on the underwriting side, the early claim adopters have primarily chosen to develop their own in-house customized models and scoring engine capabilities. Although a considerable investment of time, internal resources, and capital is needed, the ultimate financial benefits of claim predictive modeling have been impressive. Early adopters of claim predictive analytics are achieving four to eight percent annual reductions in their loss ratios. These savings have been achieved in part by the redeployment of supervisory resources and claim management improvements by nurses and SIU referrals.
The Analytics Discussion
The conversation surrounding claim predictive analytics has quickly moved beyond if it is a viable solution, to how an organization can rapidly deploy these types of solutions in order to reap the savings benefits.
One significant lesson for organizations who have already implemented claim predictive models is that much of the data needed to develop significant segmentation power is actually available very early in the life cycle of a claim.
Even at FNOL, when much of the claim information is still unknown, the segmentation power of the models is noteworthy. For the loss time indemnity models and loss time medical models that we have developed at FNOL for workers' comp clients, the average claim severity for the best ten percent of claims is often over 35 percent better than average. For the worst ten percent of claims, the average claim severity is often over 40-percent worse than average. For medical-only models at FNOL, the average claim severity for the best and worst risks tighten by about ten to 15 points on each end. At one month, with additional information, the segmentation power of the models more than doubles for the worst ten percent of claims, with loss time indemnity showing average claim severity over 100 percent worse than average.
For commercial auto and personal auto bodily injury models that Deloitte has developed for its clients at FNOL, the average claim severity for the best ten percent of claims is usually in the range of 50 percent better than average. For the worst ten percent of claims, the average claim severity is frequently over 200 percent worse than average at FNOL.
Although it takes longer to retrieve information from third-party claimants who may not have much incentive to divulge additional information in a timely fashion, the segmentation power of the models is still significant when external data is leveraged to supplement the traditional internal data available at FNOL. So again, it is no longer a matter of if the models work, but how an organization can leverage the model's segmentation power to develop a competitive advantage in the marketplace.
Claims on a Cloud
In the current economic situation in which top line growth is compressed and claim organizations are under the microscope to run as efficiently as possible, it takes a very compelling business case to launch a major analytics or predictive modeling effort. The improvements in claim predictive modeling have also come at a time when many claim organizations are already looking to upgrade or replace their core claim management capability. As a result of these efforts, claim organizations have allocated a large part of their budgets and IT resources to these types of initiatives.
So how can claim organizations take advantage of advanced claim analytics opportunities when their IT resources and budgets are constrained? How can smaller companies reap the benefits and pursue leading capabilities being derived from advanced analytics initiatives? How can claim organizations on a smaller scale and with smaller claim volumes stay in the game? Now there are viable alternatives, no matter the size of the organization.
Deloitte worked with Experian to develop a set of claim predictive analytics offerings that include a hosted solution for insurance companies and self-insureds. The firm says this solution is designed to bring the best of two worlds together—a tested, production-based suite of claim predictive models hosted in a secure, technical environment. This private cloud setting can offer many of the same benefits of a custom-built, stand-alone solution, with five distinct potential advantages:
- Deployment to results cycle time is reduced from years to months. This can in turn translate to a faster ROI for claim organizations.
- Costs can be transformed from a heavy, front-end investment to a more predictable, per-transaction basis or a 'pay as you go' model.
- Technical resource and integration requirements are virtually eliminated.
- Implementation, data, and deployment risks are reduced and shared without compromising security.
- The available data universe may be much larger and more diverse than that of a stand-alone, custom-built implementation.
The basic mechanics of how claim predictive models function in this hosted environment begin with collecting a limited ,but highly prescriptive set of initial data at FNOL (and/or designated points thereafter). This information typically consists of data captured at FNOL, and from other basic sources such as policy/insured/claimant data and external third-party sources.
This captured data is sent in real-time to the hosted environment for analyses, comparison, and scoring. The score incorporates knowledge from a much larger and more comprehensive database than most organizations have access to, thereby increasing credibility. A score and the associated reason codes explaining the drivers behind the score are produced and returned quickly to the insurance company or the self-insured's claim environment for immediate use by the claim handler.
The model output received from the hosted environment can either be referenced independently, or integrated into the organization's core claim business processes and work flow. Re-submission and re-scoring of claims based on pre-defined claim events, scoring triggers, and as the claim lifecycle evolves can also be designed into the iterative process.
Clearly, there are both functional and technical options available for insurance companies and self-insureds to enable claim predictive modeling capabilities without burdening or relying solely on their IT departments. This is excellent news for claim executives who have been struggling for years to find the right balance between resource allocation, straight-through processing opportunities, and identifying the claims with the largest loss potential before they actually become large losses.
A Competitive Advantage
Organizations willing to implement claim advanced analytics "on the cloud" are aiming to develop a competitive advantage over those who may not have the information technology bandwidth or financial resources to turn competitive modeling insight into actionable business results. As Gartner shared at its 2010 Gartner Symposium/ITxpo, their analysts believe that cloud computing and advanced analytics are the top two strategic technologies and trends for most organizations this year.
As insurance companies and self-insured organizations successfully leverage both strategies to improve the claim management process from assignment to resolution, the savings in terms of improved loss costs and reduced expenses, fraud mitigation, and resource optimization can be tremendous. More importantly, providing analytics-based insights into the claim resolution process is ultimately the better solution for injured workers and claimants. By identifying the right claim and the right resource at the right time, companies will be better able to reach the ultimate goal of helping an injured person get back on his or her feet as soon as possible.
Jim Kinzie CPCU, ARM, is a senior manager at Deloitte Consulting LLP in Irving, Texas and a leader in Deloitte's claim and risk management practice.
Kevin M. Bingham is a principal at Deloitte Consulting LLP in Hartford, Conn. He is a leader of Deloitte's claim predictive modeling practice and chairperson of the American Academy of Actuaries Medical Malpractice Subcommittee.