Analytics is certainly not new to the insurance industry. Itcould be argued that the first mortality tables developed in the18th century were analytics. However, the adoption rate of businessanalytics within insurance has been slow.

Today, predictive modeling and forecasting are used by actuariesfor pricing, but few insurance companies have applied analytics ina real-time or near-real-time operational environment.

The "analytical insurer" is an insurance company using analyticsthroughout its organization to improve business performance. It hasfour major components:

• Claims analytics
• Customer analytics
• Channel analytics
• Product analytics

Claims analytics

Claims are by far the biggest expenses within a p&cinsurance company and can account for up to 80 percent of aninsurer's revenue. The way an insurance company manages the claimsprocess is fundamental to its profits and long-termsustainability.

Claims analytics is the process of analyzing the structured andunstructured data (i.e., email, adjuster notes, medical records orpolice reports) at all stages in the claims cycle (FNOL to payoutto subrogation). Since up to three-quarters of claims data isunstructured data, the ability to analyze it is essential toimproving the claims cycle. 

Claims fraud is already a widespread problem for insurers, andin a difficult economy it tends to accelerate. The most effectiveway to combat both opportunistic and organized claims fraud is touse a combination of business rules, predictive modeling, anomalydetection and social network analysis. Using analytics will notonly detect, but also prevent fraud before claims are paid.

Insurers often only receive a fraction of not-at-faultsettlement costs because they don't pursue subrogationopportunities. Using claims analytics, insurance companies canidentify known subrogation characteristics and optimize associatedactivities.

Finally, some insurers are beginning to use analytics tocalculate a litigation propensity score. Claims that involve anattorney often double the settlement amount and significantlyincrease an insurer's expenses. Analytics can help insurersdetermine which claims are likely to result in litigation andassign those claims to more senior adjusters, who can settle theclaims sooner and for lower amounts.

Customer analytics

With little differentiation between product offerings, it isextremely challenging for insurance companies to retain customers,resulting in poor loyalty levels and increased acquisitioncosts.

Customer analytics is the ability to segment customers accordingto their likely buying behavior and potential profitability.

As the cost of acquiring new customers continues to rise,insurance companies are using analytics to develop customerretention programs. Data mining techniques can be used to predictthe likelihood that a policyholder may not renew or lapse his orher policies. By proactively using this information, insurers cancreate marketing campaigns to prevent policy cancellation.

Another concept that insurance companies are beginning toembrace is the use of customer lifetime value. Insurance companiescalculate the net present value of the customer based over anextended period, say five to 10 years. Knowing the lifetime valueof a customer is a benchmark for companies on how much they wouldor should be willing to invest to acquire/retain a customer.

Channel analytics

The way that people buy insurance is rapidly changing. Asinsurance companies begin to implement multichannel integrationstrategies, the challenge for the insurance company is to determinethe right distribution method for each customer.

Channel management is certainly not a new concept; however,management decisions are driven on historical, periodic performancereporting. Product managers and field marketing can only react oncean agent persistency rate or other KPIs fall below an unacceptablerate, well after corrective action should have been taken. Channelanalytics help to conduct "deep dives" into causal factors, whichin turn require access to predictive data and forward-lookinganalyses.

Product analytics

In many lines of business, insurance has become a commodity withcustomers often choosing insurers purely on the basis of price.Product analytics is the ability to analyze the impact onprofitability when there are new products and changes to existingpricing structures.

Product pricing or ratemaking is undergoing a significanttransformation. Insurers are increasing their use of advancedanalytical tools, like generalized linear modeling, to get moregranular rates. As insurers capture more and more data, the morethey will learn and predict – delivering better results. In fact,some insurance rates will become very personalized as insurersbegin to use data from in-car computers, weather patterns and evenroad conditions to determine premiums. 

In addition, insurers are building analytical models thatanalyze the impact of proposed rate changes on policyholderretention and conversion rates for an existing book ofbusiness. 

In a highly competitive market, it is vital for insurancecompanies to minimize inefficiencies and reduce losses to protectprofitability. By using data proactively, companies can betterunderstand their business, detect areas for improvement and takeremedial action. Analytics has become fundamental for insurers toremain competitive.