When it comes to claims processing, insurers are obsessed withcycle time.

They count the days it takes to make a claim adjudicationdecision, the minutes it takes to complete the loss intake process,and the seconds it takes to process a transaction. Especially inhigh-volume environments, time is money.

In the wisdom of insurance claims executives, faster claimpayments generally equate to better customer satisfaction andloyalty. Anything that slows the process is burdensome and costly.Insurance companies are always looking for ideas on how to improveor optimize the claims process.

Related: 4 steps to building a strategic analytic culture inyour organization

Predictive insurance claims processing, or claims analytics, isthe process of analyzing structured and unstructured data at allstages in the claims cycle to make the right decision, at the righttime, for the right party.

Here are four areas in which applying analytics to the claimsprocess can have the biggest effect:

1. Fraud analytics

Fraud is a large and growing problem for the insurance industry.Most research estimates that about 10% of insurance claims arefraudulent and cost the insurance industry billions of dollars. Tocombat claims fraud, insurance companies shouldimplement a real-time or near-real-time analytical engine thatcalculates the propensity for fraud at each stage of the claimslife cycle.

The fraud analytical engine must use a combination oftechniques, including business rules, predictive modeling, textmining, database searches and exception reporting. In addition,insurers should consider network link analysis technology, whichanalyzes all historical claims to quickly discover organized fraudrings that might otherwise take months or years to identify andprevent.

2. Recovery optimization

Recovery optimization scores claims at each stage in the claimslifecycle based on known subrogation characteristics, identifyingunknown characteristics and optimizing associated activities. Byusing text analytics, insurers can analyze adjuster notes or otherunstructured data to find phrases that typically indicate asubrogation case. Pinpointing likely subrogation opportunities earlier,insurers maximize loss recovery and ultimately reduce lossexpenses.

(Photo: Shutterstock)

3. Settlement optimization

Bringing consistency to the claims settlement process is animportant objective — especially for claimsmanagers who are pressured to settle faster, with transparentfairness, while using fewer resources and reducing loss-adjustmentexpenses.

Related: How to extract data to price better, expand marketsand improve underwriting

The first ongoing problem with managing claims leakage comesdown to one simple thing: Insurers have no effective way ofpredicting the size and duration of a claim when it is firstreported. But accurate loss reserving and claims forecasting isessential, especially in long-tail claims like liability andworkers' compensation. Analytics can more accurately calculate theloss reserve by comparing a loss with similar claims. Then,whenever the claims data is updated, analytics can reassess theloss reserve.

The second issue is to assign claims to the right resourcesright from the start at first notice of loss and by ensuring thatpriority claims receive priority treatment. By implementing datamining techniques to cluster and group loss characteristics (suchas loss type, location and time of loss, etc.), claims can bescored, prioritized and assigned to the most appropriate adjusterbased on experience and loss type. High severity and more complexcases are assigned to the most qualified adjusters, whilelow-exposure claims are channeled to less experienced adjusters. Insome cases, they can even be automatically adjudicated andsettled.

4. Litigation optimization

A significant portion of a company's loss expense ratio goes todefending disputed claims. Every insurer canrelate to the typical horror story claim where the passenger of anauto accident broke a finger and walked away with a $250,000settlement. With litigation optimization, insurers can useanalytics to calculate a litigation propensity score.

Claims that involve an attorney often double the settlementamount and significantly increase an insurer's expenses. Analyticscan help determine which claims are likely to result in litigation.Those claims can be assigned to more senior adjusters who arelikely to be able to settle the claims sooner and for loweramounts.

As insurance becomes a commodity, carriers need to consider howthey can differentiate themselves from competitors. Adding analytics to optimize the claimslifecycle can deliver a measurable ROI with cost savings andincreased profits; just a 1% improvement in the claims ratio for a$1 billion insurer is worth more than $7 million on the bottomline. Claims optimization also delivers intangible benefits, suchas improved customer satisfaction. And that is a win-winarrangement for both the customer and the insurance carrier.

Stuart Rose is global insurance marketing manager at Cary,N.C.-based business analytics software and servicescompany SAS.