Manish Jaiswal

Monika Vashishtha

Information is power. Right and timely information is even morepowerful. Since the early stage of corporate world, leaders havefound the virtues of analyzing the information not only to gaincompetitive advantage but also for the course correction.

In recent years, there has been much discussion about the meritsof predictive analytics (PA) in project management that enablesmanagers or business leaders to achieve scope, time and costbalance.

So, what is PA and how far it is used in the insuranceworld?

• Is it informative dashboard - MIS?
• Is it business intelligence?
• Is it an audit to find and reduce errors of agiven and approved process?
• Is it parallel computing?
• Is it a new version of game theory?
• Is it a new way to achieve Six Sigma--faster,cheaper, and better?
• Is it quality assurance in a new avatar?

Our experience is that predictive analytics is a summary of all,particularly so in the insurance project management world.

We all know the five stages of project management--initiation,planning and design, execution, monitoring and controlling, andclosing. While project management skills are obviously importantfor project managers, interestingly the methods and tools thatproject manager's use can be helpful for everyone.

A 'task' does not necessarily have to be called a 'project' inorder for project management methods to be useful in its planningand implementation. Even the smallest task can benefit from the useof a well-chosen project management technique or tool, especiallyin the planning stage.

Project management methods and tools can therefore be useful farmore widely than people assume. One such interesting tool ispredictive analysis, especially considering its successfuldeployment in the insurance world.

According to Wikipedia, "Predictive analytics is a broad termdescribing a variety of statistical and analytical techniques usedto develop models that predict future events or behavior.Predictive analytics encompasses a variety of techniques fromstatistics, data mining and game theory that analyze current andhistorical facts to make predictions about future events".

In the PA world of insurance project management, predictivemodels exploit patterns found in historical, empirical, andtransactional data to identify risks and opportunities. Thecombination of data and modeling expertise gives the unique abilityto create most effective predictive models for insurance industry.Better analytics and tools that incorporate new data points willcontinue to drive both lift and efficiency, translating into moreproficient policy administration, improved cost estimation, smarterportfolio management and of course better service delivery. Allthis will lead to less claim ratio and operating profits for thecarriers.

"In the earliest stages of adoption, predictive analytics waspredominantly used in claims within the commercial property andcasualty space, says Jim Haley, CMO of Valen Technologies. "Today,it is quite common to see insurers use predictive analytics tosupport claims reserving issues as well as to identify fraudulentactivities within active claims".

Advanced analytics solution quickly identifies the root causesof errors in back office processes like intake, policy binding,underwriting, claims entry, claims adjudication, statement ofhealth, customer care, etc. A mature PA tool could deliver 25percent or more quality improvement in two to three weeks. Thus,leading insurance carriers and outsourcing providers are embracingthe solution.

Why and how?

PA can reveal unknown underlying patterns to known qualityproblems that can help carriers, BPO firms or project managersquickly address these problems.

PA analysis is significantly more accurate than existing manualmethods in detecting errors in the sample analyzed. Manual QC maynot detect approximately 25 percent of the errors detected byPA

For the dental claim project, PA can go from raw data tofinished analysis reports in less than 24 hours. A similar manualanalysis would take significantly more time

PA not only reduces operating costs while further improvingquality, it could open up a completely new value proposition

PA could enable a differentiated sales strategy or even become asignificant additional source of revenues

Another big challenge is to convert the theory of PA intoeffective and sophisticated software algorithm. Unless we achievethat, all the virtues of PA will be on paper or at a limited space.Naturally, the moment we talk about software or IP platform, we aretalking about set of bright and smart people who could convert theinsurance business processes into software.

This IP should have flexible rules engine and could be placed onthe given policy administration system, underwriting, or claimsplatform being used by the carriers. So, creating astate-of-the-art system is not good enough in isolation but itshould be interfaced with the legacy system platforms or legacyinsurance business processes.

It is interesting to note that PA systems evolve with time andlines of business they have been exposed to. We are not sure if onesize could fit all. To dwell further, means that a PA systemdesigned for health insurance may not work for life orproperty/casualty insurance. On theory it should, because we havelearned the definition of "system" is 'garbage in and garbage out',so any PA system should work perfectly fine for any business or forthat matter any industry as long as there is a historical orempirical data for the work flow.

Not really, though, because a PA system has virtues ofartificial intelligence, thus it grows with time.

A shift is taking place. As insurance companies continue tobecome less product-focused and more customer-focused to gaincompetitive advantage, PA and advanced PA are becoming handy. It iseasy to talk about competitive advantage or aspire for largerrevenue vis-?-vis last year but we all know, it is not so easy.Perhaps the only solution is exceptional service by exceptionalpeople. PA is needed to achieve that critical differentiation inthe market place.

Practical Usage of Predictive Analytics in the InsuranceWorld

Marketing

• Helps in direct marketing
• Helps in CRM
• Helps in cross-sell
• Helps in product prediction

Predictive Analytics (PA) software can comb through current andpast customer service calls in search of speech patterns thatindicate dissatisfaction. Carriers can home in on that data todetermine what is driving customers to call. Policies andprocedures can then be put in place to correct issues and increasecustomer satisfaction

Underwriting

PA helps combine clients' data with historical risk andeconometric information in proprietary analytical database tools tobuild, deploy and monitor models for improving underwriting andoptimizing premium audit processes

Sales and Distribution

• Producer compensation
• Training and guidance

PA helps engage more closely with their distribution outlets andpartners to align and share new, sophisticated information

Pricing

• Pricing strategies and profitability
• Improve pricing strategies, risk selectionand profitability
• Predictive analytics drives profitabilitygap

Claims

• Fraud Detection
• Helps in adjusting loss reserve funds
• Helps in prioritizing claims
• Identify high-severity workers' comp claimsbefore they become costly, reducing settlement lags and claimspayout
• Automatically assigning adjusters accordingto priority and skill set
• Helps in subrogation
• Helps in e-discovery and litigationsupport

Collection Analytics

• Delinquent customers who do not make theirpayments on time
• To ensure premium to exposure accuracy

PA provides the ability to predict the future outcome byanalyzing the past pattern or data

PA is a great tool to predict correct pricing and highlightrisk. To achieve true success of PA in the insurance space,actuaries, analysts and underwriters need huge computing power torun the sophisticated models

PA could be used by insurance leaders to respond effectively tonatural disasters by repositioning assets and people.

Manish Jaiswal, ([email protected])is national sales manager for insurance outsourcing and BPOsolutions for Affiliated Computer Services, Inc., a XeroxCompany.

Monika Vashishtha, PMP ([email protected])is process and performance manager, Global Change Management Group,Thomson Reuters.