Fraud has been a significant cost drain for many organizations across industries and Insurance is no different.
“Forty-five percent of insurers estimated that insurance fraud costs represent 5-10 percent of their claims volume, while 32 percent said the ratio is as high as 20 percent.”1
“Auto insurers lost $15.9 billion due to premium rating errors in private-passenger premiums in 2009”2
The fraud can be initiated by employee of an insurer, broker & agent, and customers (perspective and existing).
Two common types fraud in Insurance are Application Fraud and Claim Fraud
Application or Underwriting Fraud
An applicant furnishes incorrect or false information to lower premium to the policy being applied for. For example, a driver, Manu, applies for auto insurance and fills up the application. The insurance application form requires him to provide his drinking habits and age. He provides false information, so that his premium is low. In other scenario, he provides incorrect information about previous policy. This is an example of Application Fraud.
Insurance provider requires building mechanism to tag some of the applications as fraudulent based on information provided by the applicant. An accurate predictive or machine learning model can calculate probability of an application fraud.
Some of the customers misuse systems and processes by providing incorrect information for financial gain. Claim Fraud occurs when customers applies for reimbursement or claim without eligibility for claim. They forged documents to justify their claim. And in some case the claimants exaggerate the claim amount.
For example: A health insurance holder, Romney, got admitted to a local hospital. He incurred medical expense of $3700 but colluded with hospital personal in getting medical expense receipt of $5723. He has applied for claiming the amount to his health insurance provider.
Challenges for Insurance providers are to manage customer experience on one side and expense due to fraudulent cases on other side.
Due increased competition and customer expectations, the insurance providers have to simplify and speed up the application and fraud process. If more applications or claims are tagged for decline or review, it will increase operational cost and also customer dissatisfaction among genuine customers.
Also, more and more insurance providers are moving to digital channels and the decision has to make the decision faster.
Typically, there are a few ways to improve decision making to identify fraudulent applications and claim requests – improve modeling process, select best modeling technique and leverage enriched data sources.
Data from government agencies, Social Media and external data providers can help in getting more reliable and probably accurate information for predictive model.
When historical information on fraud is available, supervised statistical & machine learning techniques such as regression, neural network, random forest, and support vector machine (SVM) can be used. In other scenarios unsupervised or subjective segmentation techniques such as k-means clustering, random forest (for anomaly detection) and Self Organized Maps (SOMs) could be tried.
Trend in Fraud Analytics in Credit Card