By BRUCE S. ZACCANTI, a principal in the Insurance and Actuarial Advisory Services practice at Ernst & Young; GARY T. CIARDIELLO, principal in the practice; and JUSTIN J. BRENDEN, an executive in the practice
With industry combined ratios across many lines pushing well above 100 percent, insurers are under increasing pressure to improve profitability. Many have exhausted the traditional avenues of tightened underwriting and expense control.
Given this market environment, companies are turning to advanced analytics to maintain their profitability and competitive position. Since predictive modeling has been widely adopted for both pricing and underwriting purposes, management teams are now looking for the next operations area to apply analytics: claims and claims expenses.
What questions can analytics answer regarding claims management?
-- Are we spending more than we should to settle claims?
-- Are there specific claims that could be handled more efficiently?
-- If we could identify inefficient claims earlier, what actions could we take?
-- Are we assigning claims to the appropriate adjusters based upon skill and experience?
WHAT DRIVES CLAIMS DEVELOPMENT?
The issue of unexpected loss development is not addressed by current claims practices for a number of reasons. First, recognition of these "problem claims" is highly subjective, and claims personnel may vary significantly in opinion and experience, even when provided the same fact pattern. In addition, claims personnel are often not equipped with the appropriate data to evaluate loss development.
In this era of expense reduction, claims departments are under increased pressure to produce better loss ratios with less resources and training while the claims themselves are becoming more complex. Higher case loads and more involved claims make it difficult for adjusters to step back and objectively determine which claims should be prioritized for management.
In addition, the improper use, or lack of use, of certain claims department practices may actually increase payments on claims unnecessarily, a concept known as "claims leakage."
Predictive modeling can ease this process by allowing for simultaneous consideration of many variables and quantification of their overall effect. This includes recognition of patterns that are difficult for even the best adjusters to recognize due to the vast amount of information available and constraints such as time and size of case loads.
It can be used to quantify the impact to the claims department resulting from the failure to meet or exceed claims service leading practices and to identify the root cause of claims leakage. Further, current claims can be scored for loss development potential to identify the drivers of unexpected development and create an effective way to triage claims.
Therefore, proper use of predictive modeling will allow for potential savings across two dimensions: early identification of potentially costly claims and recognition of claims practices that are unnecessarily increasing payments.
The path to improvement and utilizing predictive modeling techniques is a four-step process:
1. Model construction. The construction of the predictive model should follow a disciplined process of claims-data gathering, assembly of a historical database, selection of predictor variables and testing of a model.
2. Claims triage and mitigation. Adjusters should prioritize their case loads based on the claims that have the highest potential for future loss development and create specific loss mitigation steps based on the reason codes that are produced by the predictive model.
3. Claims leakage analysis. Some of the predictive model cost drivers will be related to leakage root-cause claims drivers. The remaining leakage areas will be discovered through a detailed review of claims that develop further than the model predicted. This remaining unexplained development is subjected to a claims leakage root-cause analysis that will identify additional root-cause drivers of development not already captured in the model.
These drivers will lead to insight into the areas of improvement in current claims department practices. This targeted approach is superior to a typical claims review because it focuses on the adverse development that is not statistically explainable by patterns in historical data.
4. Process improvement. The claims leakage analysis will naturally drive improvements by identifying actionable changes that can be made to the claims process. Furthermore, this intelligence could be channeled back to the underwriting process, as the claims and underwriting cost drivers are often intertwined.
Once cost-saving opportunities have been identified by this four-step predictive analysis, claims departments can convert those savings into real dollars, for instance, by applying loss mitigation strategies to specific claims identified. They could change claims service standards and practices to reduce unnecessary payments on future claims. Another step is to conduct claims training to focus on implementation of leading practices developed from predictive analysis. Or claims managers can conduct quarterly quality assessment reviews to test that remediation efforts are mitigating and eliminating claims leakage and improving claims adjudication performance.
The application of these approaches can lead to substantial savings--estimated loss-ratio savings of 1 percent to 2.5 percent--not to mention improved claims-handling practices.
June 1, 2011
Copyright 2011© LRP Publications