In today's economy, where consumers are focused on valuefor money, property and casualty (P&C) insurers perpetually strive toreduce the cost of handling claims. Among other techniques, thisusually involves an enhanced focus on streamlining business processes and tackling fraud. Carefully managing outsourcing options andsuppliers are other common ingredients in an insurer's overallsolution.

A growing number of insurers are finding clever ways to use gooddata to bolster a competitive advantage made possible by enhancedcustomer service—all while reducing claims expenditures. Imaginethe benefit of being able to move toward straight-throughprocessing of claims at first notification of loss (FNOL), with confident knowledgethat the claim was neither exaggerated nor blatantly fraudulent.This sounds ambitious but is within reach for insurers whocarefully align business strategies with the appropriatetechnologies.

Minimize Fraud
Unfortunately, we are all living in a less-than-completely honestworld, where fraud is rising. In fact, many would say that scammersinvolved in organized crime rings especially view the P&Cinsurance industry as a low-risk, high-gain market.

Through the use of next-generation fraud detection technology, some insurers have been able tosignificantly increase the number of claims processed withoutadditional checks by maximizing the value in available data.Savings are achieved by impacting three key metrics:

• The total fraud detected. Carriers typicallyestimate that data allows them to capture twice the volume comparedto the use of traditional systems and human examination.
• The false positive rate. This can be reducedwith a noticeable improvement in the ratio of claims flagged andthen investigated, denied, and possibly reported.
• Overall claims efficiency. On average,investigators take one fifth of the time to investigate a claimthat is already flagged as potentially fraudulent.

Data Removes Doubt
A consistent set of data approaches have been identified to providemaximum impact:

1. Data aggregation and networkanalytics.
Traditional approaches use rules engines, matching techniques, orpredictive analysis at the claim level only. Next-generation toolsaggregate all historic policy and claims data into a data warehouseof networks, and apply all three of these techniques, in real-timeor batch, to the claim, single historic customer view, andnetwork.

Is a vehicle accident with three whiplashes fraudulent?Possibly. What if that policy is connected to others by key piecesof physical or behavioral data, and each of those other policieshave had claims in the last few months involving multiple neckinjuries? It is almost undoubtedly fraud. Conversely, followingthis exhaustive linking process, a claim that is on a network wherea number of customers have had policies with the insurer forseveral years without claims has a higher probability of being agenuine accident. By networking all of your data, you have supremeintelligence to significantly improve the automated identificationof fraudulent or genuine claims.

2. Multiple lines of business.
A number of insurers have demonstrated that building networks ofcustomers and activities across multiple lines of business provideseven further customer insight and intelligence. A customer with arepeated incidence of suspect home claims is more likely to make asuspect vehicle claim or travel insurance claim. At a larger scalea number of fraudulent vehicle insurance claims have identified largefraudulent commercial insurance claims.

3. Capture intelligence and learn.
All investigations provide invaluable intelligence, it is importantto capture every outcome or interaction with your customer, whethera claim is denied, marked for additional attention or cleared. Thisinsight is added to the networks and allows the system to learn andadapt scoring to improve accuracy. A networked database also allowsthird-party fraud flags to add far more value as they can be usedto enhance risk scores even if they are not directly matched withthe claim in question.

4. Use automated scoring at every step.
Cost can be reduced if you can confidently identify at the earliestpossible opportunity which claims need further investigation andwhich should be paid. The system should re-score the claim everytime any additional information is obtained throughout the claimshandling process. This ensures that time is not wasted inunnecessary investigation and customers are not kept waiting forsettlement.

5. Eliminate organized crime.
Insurers who implement networked analytics solutions find thatorganized crime represents a disproportionally large volume ofclaims fraud. It becomes very apparent that what initially appearto be opportunistic frauds are frequently connected and part oforganized crime. A networked analytics approach is the ideal way toidentify and deal with the conscious, pre-meditated activitiesassociated with organized fraud.

6. Leverage free textdocuments.
Many insurers fail to make use of free text associated with claims,policies, customer interactions or contracts. This text can bemined and used in multiple ways for example, words and phrases canbe used in risk scoring to better predict fraud and entities can beextracted from the text automatically to enhance networked data.Investigators can search huge volumes of text documents to findevidence, historic behavior or commonalities in seconds. Textanalysis, categorization and heat mapping by claim types andgeography can help to identify fraud or risk hot spots. The abilityto process and integrate text is especially important in areas suchas commercial, medical and liability related fraud.

7. Identify and remove supplier fraud.
Suppliers represent a significant share of claims spend, fromgarages, to doctors, lawyers and accident management companies. In many cases theseare enablers of organized fraud, but they can also be fraudulent intheir own right. By networking all of the claims around theseentities and then performing a range of automated analytics such asoutlier analysis, consistently anomalous behavior andidentification of links to known frauds the identification of, whatis frequently, large-scale fraud within the supplier base can beuncovered.

8. Prevent fraud from re-entering thesystem.
Fraudsters are very persistent and once they have been able tosuccessfully deceive an insurer they will continue their attacks.By capturing denied claims or suspects onto the networks ofcustomer data it is possible to run a match at policy inception.This can flag any connection of a new customer to a previousfraudster or ring of organized crimes and queue that particular applicationfor exceptional checks before accepting the application. The sameapproach can be used with third-party known frauds or sanctionlists to prevent money laundering.

9. Spot fraudulent brokers and insiders.
Sophisticated fraud rings will often work through brokers or placeinsiders within insurance operations to perpetrate volume fraud.For example, by adding the user ID's of the staff members whoprocessed any part of the policy, to the networks of customer data,it is possible to identify any staff who are showing strangebehaviors or who are overly connected to fraudulent activities.

10. Sanctions listchecking.
To protect from potential reputational damage and financialpenalties from the regulators, insurers have to ensure they operatean effective and auditable sanctions list checking process. Byimplementing a solution which provides a 'single view of customer'it is possible to effectively confirm an individual's identity andcheck them against any non-trade lists and reduce the burden ofeffective regulatory compliance.

Further Leverage
The depth of insight that is obtained by linking data across linesof business and through history to produce complete single views ofcustomer or supplier can be used for other purposes too. Policypricing, for example, could be dynamically adjusted based on risksto improve the quality of the customer base and marketing campaignscan be optimized through the analysis of cross product adoption oridentification of 'influencers.'