A typical auto claim process starts with a phone call froma policyholder who has just been in a car accident. The carrierrepresentative collects details about the accident, and the claimsprocessing system passes information to a claims adjuster's queue.The claims adjuster then starts the investigation and may orderincremental data that he or she thinks is most appropriate for eachcase. However, this process is labor-intensive. It may take 45 daysor more to close the claim.

Now consider this scenario: an agent receives a phone call from a person who has just been in a car accident.The representative immediately sees all of the relevant data aboutall involved parties as it fills the screen through a data prefillproduct for quick validation and customer confirmation. The agentinstantly confirms the person's name, address, and vehicleidentification number (VIN), as he or she collects details aboutthe accident. Once the accident details are captured, the data isevaluated against an external database that indicates the claimantactually has coverage with multiple carriers. The claim isautomatically directed to the carrier's subrogation unit forfurther investigation.

Scenarios like this one are surprisingly uncommon. In areas ofthe business like personal lines, quoting, and underwriting,carriers have embraced data and analytics to improve profitability and reduce costs.Yet, they have not applied the same approach to claims—where thevast majority of a carrier's premium dollars are spent.

Data and analytics can help carriers create a more efficientclaims process: one that is both cost- and time-efficient, and thatminimizes losses related to fraud while enhancing customer service. To reap the fullbenefits, insurance carriers must proactively supplement theirinternal policy-level data with external data.

Intuitively, carriers know the value of external data to theclaims process, but they typically use it in a reactive manner.For instance, special investigation units (SIUs) order point-in-timeinformation from police reports, medical reports, and publicrecords data. However, by using external data reactively, carriersare leaving holes in the claims process—paying potentiallyfraudulent claims, missing subrogation opportunities, and allowing severe claims toescalate in the hands of inexperienced adjusters—while simpleclaims languish on adjusters' desks, driving up handling costs andnegatively impacting customer service.

In contrast, a proactive claims handling approach takes fulladvantage of multiple data sources and analytics engines. Fromfirst notice of loss (FNOL), carriers can evaluate the claimand route it to the most appropriate person or department: sendingsuspect claims to SIU, subrogation opportunities to investigators,potentially severe claims to experienced adjusters andfast-tracking low- or no-touch claims for payment.

It doesn't stop there. After all, the claims process is dynamic,and the processes that support claims processing need to be equallydynamic. As claims are updated with new information, a proactiveapproach gives carriers a way to easily re-assess and re-route eachclaim, ensuring that each one is still in front of the right personat the right time. Advanced AnalyticsTechniques
Advanced analytics techniques can help a claims organization to developmore sophisticated, efficient ways to manage the claims process.Here are some commonly used advanced analytics techniques:

• Predictive models use algorithms to identifypatterns in data. Claims are scored and then routed to theappropriate claims area, such as SIU or subrogation units.
• Business rules alert carriers when specificsituations arise. These business rules can be customized accordingto a carrier's particular needs.
• Identity matching monitors all claims forentities—people or VINs—that are on a watch list. Carriers areinformed when the entity appears on a claim.
• Data search enables carriers to searchstructured and unstructured data for words, phrases and names. Thistool is especially valuable, as unstructured data is notoriouslydifficult to parse.
• Relationship analytics find links betweenclaims or claimants. This can be an immensely powerful tool forfraud investigations—for example, to detect links between claimantsand known suspicious entities. When combined with external data,this can be particularly powerful by identifying relevantrelationships that aren't visible to a carrier using their dataalone.

These tools can be even more powerful when used in combinationwith each other to take advantages of the strengths each toolindependently brings. Identity matching and predictive modelscores, for example, can be used to enhance business rules toreduce false positives and improve outcomes.

Pulling External Data
Carriers can reap the true benefits of data and analytics byaugmenting their internal policy and claims data with external datasources.

"Insurers need to start leveraging the external data that isavailable in the marketplace," advises Deb Smallwood, founder of Strategy Meets Action, aninsurance-focused research and advisory firm. Smallwood recommendslooking at the entire claims process to see how external data canbolster an insurance company's internal data capabilities: "Ithelps to start at the beginning of the process," she adds. "Uponsubmission of a claim, insurers can pre-screen for fraud. They canalso use data prefill capabilities, for example, drawing fromaccident reports to help populate and validate information in theclaim."

Often, claimants are in a highly stressed state when they reportan accident, which can adversely affect the accuracy and completionof the report. With insight from external data sources, customerservice representatives can verify accident and policy informationwhile offering more personalized customer service. More critically,the validated data results in greater accuracy of the claim detailsso the carrier can process the claim in the most efficient way.

With a validated claim, carriers can applypredictive analytics to fast-track low- or no-touch claims topayment, minimizing the time and cost of handling. They can alsoquery external data sources for information about a claimant'shistory of prior claims. Excessive history may merit furtherattention from SIU. Additionally, carriers can find out if aclaimant has coverage from other carriers, unlocking possiblesubrogation opportunities.

In the area of fraud detection, external data and multipleanalytics tools are a tremendous combination. "Fraud detectionneeds to get pushed into the earlier stages of the claims process,"says Smallwood. "You still need SIU to look at aggregate data fortrends, behavior, and fraud rings; however, insurers need to startto apply analytics on the front-end for real-time fraudalerts."

Predictive models can look for data patterns associated withfraudulent claims, notifying carriers of suspicious activity.Carriers can create business rules to isolate claims that meetcertain criteria; for example, to find cars that have been reportedstolen and discovered burned. Identify matching can monitor claimsthat reference a vendor or party of interest, and relationshipanalytics can find links between people and claims. Data search isa particularly valuable tool, enabling carriers to search throughunstructured text—adjuster logs, emails, and incomplete policyadministration forms to name a few sources—for medical terms,names, or phrases.

Furthermore, public records contain immense information that canhelp carriers handle claims more effectively. By proactivelymonitoring public records for financial distress, bankruptcies,liens, judgments, criminal records, and death records, carriers canuncover valuable information. It is not uncommon for carriers todiscover, upon monitoring public records, that they have beenpaying disability claims to deceased claimants.

Finally, medical data is notoriously underused in the claimsprocess, but it can be tremendously useful. Medical data can helpcarriers determine the possible severity of a claim and can helpidentify providers who consistently exaggerate or invent injuries.Carriers can apply relationship analytics to medical data to helpidentify fraudulent ring activity.

Tip of the Data Iceberg
Rather than applying a linear attitude to the claims process,carriers should adopt a dynamic, data-driven approach ofcontinually evaluating and routing a claim as information is added.This next-generation approach to claims handling relies onproactively using external data throughout the claims process, andapplying advanced analytics to route the claim to the mostappropriate person or department.

The benefits of doing so are tremendous. By paying out simpleclaims quickly, carriers can minimize their handling costs whileenhancing customer service. Moreover, by flagging and routingclaims as they come in, carriers can be more confident that theyare handling the claim in the most efficient way. Aside from theinherent cost savings, this can unlock subrogation opportunitiesand detect fraudulent activity while there is still time toact.

Smallwood concurs: "The industry is at the tip of the iceberg interms of the opportunities for full use of data and analytics inthe claims process. Right now, it offers a competitive advantage.Soon, it will become the norm. The insurers that get on board andstart to use it now will be in a better position when the marketpicks up."

Every carrier aims to handle claims quickly, fairly andaccurately. They invest heavily to earn their premium dollars,spending the majority of their dollars in the claims process. Byproactively integrating external data and using advanced analytics,carriers can reduce costs and ensure that they are making the mostof their resources. This means getting the right information to theright person, at the right time.