New technological developments are seeking to resolve three ofthe biggest headaches in insurance: improving customer service,reducing the cost of handling claims, and detecting fraud.

In their ongoing efforts to be more competitive and profitable,insurance companies are undertaking several initiatives to improvetheir claim-handling processes. Foremost among these is improvingclaim-handling efficiency. The claim-handling process is expensive,accounting for around 20 percent of the total costs of an insurancecompany.

Companies may strive to decrease these costs by offeringfast-track claim handling. By settling 50 to 80 percent of claimsduring initial telephone conversations, insurers can avoidinvestigations and the gathering of additional information, as wellas expensive follow-up contacts. In some cases, 60 percent of thephone calls into claim-handling centers are from customers seekinginformation about the status of their claims. Companies that allowcustomer self-service can further reduce claim costs by havinginsureds file their own claims via the Internet and handling theseclaims instantaneously, often without human intervention.

Improving service levels to customers also is a common goal. Theability to offer customers a range of convenient options to notifycarriers of claims, such as direct mail, call centers, or online,and to respond quickly to claim notifications allows companies todistinguish themselves and acquire and retain customers better thantheir competition.

Decreasing the Cost of Fraud

Although it is estimated that up to 10 percent of all claims arefraudulent, insurance companies are able to uncover only 0.5 to 1percent of the suspected fraudulent cases. The potential forimprovement is huge. In the past, insurance companies were notinterested in detecting fraud; they simply would accept fraud,increasing premiums to make up for the increased costs of claims.

Two trends are changing this now. Increased pressure fromgovernment and a growing disapproval among the public are fosteringa widespread belief that fraud is a crime and that it isunacceptable that other citizens should pay for these costs. Inaddition, reducing the cost of fraud allows insurers to offer morecompetitive premiums.

Technology also is coming to the rescue. Predictive software canhelp insurance companies uncover two to three times as manyinstances of fraud, whilst enabling them to staff the first line offraud detection with the people who do it best: the branch andcall-center teams who speak to customers every day. Such astrategy, if implemented correctly, can enhance fraud detection andcustomer relations, and does not require vast investments ininfrastructure or personnel.

The key lies in a program that can be integrated into existingclaim-handling systems and provides claim handlers with advicealerts when they enter new claims. This advice is based on experts'insights into fraud, combined with advanced analytic software.Based on this, the claim handler can decide to settle the claimimmediately, thereby offering improved service and reducing costs,or to perform a normal investigation or send the claim to the frauddetection department.

Most fraud cases rely on that most unquantifiable of humaninstincts, the gut feeling. Many fraud experts say that they canspot fraudulent claims instantly; the time spent on a case is tosubstantiate their instincts. These instincts, of course, are basedon considerable experience, but they can be boiled down to ahandful of key risk indicators that can show how each case shouldbe handled.

Although this knowledge is available within the frauddepartment, other areas of the company do not draw on it widely.Institutions can gain considerable value by interviewing expertsand building their knowledge into the claim-handling process, toflag those claims that require further investigation.

This process, which I call mind mining, can help determine thehandling of a great deal of claims, but it is not the wholepicture. Many fraud profiles are unknown to the experts but can berevealed by analyzing historic fraud data to predict future trends,a technique known as predictive analysis. Entirely new classes offraud can be uncovered using predictive analytic technology,increasing annual fraud detection rates two- or three-fold.

The fruits of the two processes can be developed into a range offraud profiles or sets of criteria that establish whether newclaims might be fraudulent. If a claim were to match any of theseprofiles, it could be sent to the fraud department for furtherinvestigation.

The next stage is to put into place a process that allows fraudprofiles to be updated on an ongoing basis, enabling theunderstanding of new fraud trends as they develop. Predictiveanalytics also is effective here. Fraud experts can delve intoclaim databases and use the technology to spot new trends. This isa simple, ongoing feedback loop of analysis and profiling by fraudexperts, followed by deployment and action within the callcenter.

Customer Service

Insurers regard the speed with which they can respond tocustomers' claims as a visible way to distinguish themselves fromtheir competitors. Setting up a fast-track claim process providesobvious customer service and sales benefits, while allowingcompanies to reduce claim-handling costs, by up to 40 percent insome cases. The success of this strategy relies on an earlyunderstanding of which claims are unlikely to be fraudulent.Without this understanding, insurers leave themselves exposed tofraud.

Many claim handlers and customer service representatives lackthe expertise to recognise fraud. Companies must consider carefullyhow CSRs can match claims to fraud profiles. In busy call centersor branches, it would be highly impractical, and unnecessary, topresent CSRs with lengthy fraud questionnaires each time theyregister new claims. Analytic and scoring software can reduce theclaim-handling process to minutes with a handful of leadingquestions, and provide immediate recommendations on whether a givenclaim is potentially fraudulent and should be handled by the normalclaim-handling process, or whether it can go through the fasttrack.

Imagine that a motor insurer's claim-handling system has beenprogrammed to flag any claims involving claimants under 25 years ofage, living in Chicago, and driving red or sports vehicles. John, a46-year-old from East St. Louis, calls in to make a claim fordamages to his car. The first half of the profile can be discardedaltogether, but John confirms that he drives a red MR2. While Johnis still on the phone, the system advises the CSR that, on thebasis of the car type and color, the claim might be suspicious andrequires further investigation. The CSR can advise the customerthat an investigator will be in touch soon, and end the call.

If however, John's car is blue, the system may determine thatthe claim is likely to be watertight and can be settledimmediately. Not only can this reduce the burden on the frauddepartment, the ability to offer genuine claimants settlements onthe spot opens the door to a whole range of new salespossibilities: an insurer is almost guaranteed a hit with acustomer whose claim has just been approved.

One-stop claim handling need not be as ambitious and demandingas its name might suggest, and it broadens customer service, sales,and marketing possibilities. Given careful investment in the righttechnology, and an emphasis on implementing the closed-loopprocesses outlined above, insurers can catch up with fraudperpetrators and provide better service to customers. How's thisfor a vision of insurance in the 21st century?

Marcel Holsheimer is vice president of product marketing atSPSS, a provider of predictive analytic technology.