The use of predictive analytics in insurance is becoming increasingly widespread as companies realize how the power of insight can impact business growth, risk management, and loss control. The number of insurers using these sophisticated models is growing daily and, there are more business capability areas that are reaping the benefits. Recent SMA research indicates that over one-third of insurers are currently investing in predictive analytics and models.
Most insurers started using predictive analytics in the underwriting area. Those that are staying ahead of the curve are continually introducing new external data sources in their efforts to glean additional insightful information about the risks they are underwriting. As the available data becomes more robust and more plentiful, there are even more opportunities to view risks from varying vantage points—gaining insights that were not previously possible.
Insurers are telling SMA about a major concern that keeps them awake at night. It is not about losing a specific risk to a competitor, but rather about a case when that same risk returns to their book of business. This is the most troubling of all situations. When you don’t understand why you lost the opportunity to write the risk initially, then you most likely do not have a full picture of why another company let it go and it has ended up on your books. The key question an insurer wants answered is, “What does another company know about this risk that we are not seeing?” This demonstrates why predictive analytics are so important.
Predictive analytics also are becoming increasingly important in the claims arena, particularly in three key areas—identification of special handling needs, assignment of the right resource, and fraud detection. Insurers are using predictive analytics early in the claims life cycle to determine if a claim should be given special attention. Using just the initial claim information that is typically associated with a claim, insurers are unable to identify many of the situations that should be getting exceptional consideration.
By using predictive analytics, insurers can run through a number of scenarios, identify early signs of potential issues, and automatically flag situations that need special handling. These flagged claims can then be assigned to an appropriately skilled claims adjuster, mitigating losses and speeding resolution.
Without the insights available with the use of predictive analytics, insurers are only able to view the traditional claims data and make adjuster assignments based on workload and past resource allocation experience. Predictive analytics afford insurers real advantage by giving them the power to capitalize on the strengths of their resources and better control loss costs.
The use of predictive analytics in the fight against fraud has gained significant traction in recent years. Fraud rings are operating with highly sophisticated tools and techniques. The battle requires a mature analytics engine that is able to consolidate a view of relationships that encompass multiple unrelated parties. Insurers are using predictive analytics during the claims intake process to identify potential fraud. Using a view of the characteristics of a claim, the nature of the claim, the relationships of the parties involved, plus a number of other connected attributes, the insurer has more control and can proactively engage a special investigation unit review in cases where it is warranted.
Business development and marketing are other key areas where insurers are reaping benefits by using predictive analytics. The pressure to grow books of business has insurers turning to more sophisticated models to determine what is possible and what will be the best fit for a particular company’s strategy and capabilities.
Predictive analytics are being used to help insurers define their options for profitable business models and to expose untapped opportunities. Once opportunities are prioritized, marketing departments are using predictive modeling to select target markets and design messages that will resonate with the desired audience.
While billing has not been a major part of the predictive analytics conversation in the past, things are rapidly changing. Attributes such as number of NSF’s, statutory notices of cancellation, reinstatements, or bill plan changes can all be warning signals for potentially unprofitable risks. In most cases, the billing area is more of a contributor to predictive models than a user of predictive modeling results.
Modern insurers are realizing the real power of predictive analytics. The investments are paying top and bottom line dividends—big ones. SMA research shows that 38 percent of insurers are increasing their spending on predictive analytics technologies and tools. Predictive analytics will not diminish in importance; these highly sophisticated models will play a major role in determining winners and losers. Insurers must continue to gain experience in using predictive analytics.
The stakes are high. These sophisticated models, coupled with the right combination of internal and external data, are providing intelligence that is increasing profitability, decreasing cost, and improving operational efficiency.