18 Oct Claims Fraud: Definition, Detection and Prevention
Every year we see an increase in the estimate cost of fraudulent claims in the insurance industry. In the healthcare industry, the?National Health Care Anti-Fraud Association?estimates that 3% of the health care industry?s expenditures in the United States are due to fraudulent activities, amounting to a cost of about $51 billion, [Other estimates attribute as much as 10% of the total healthcare spending in the United States to fraud?about $115 billion annually. In the property & casualty insurance industry in the United States the amount of fraudulent claims activity is estimated to be almost $80 billion annually. It has truly gone beyond ?big business?! The size of fraud is greater than the annual revenues of many large companies such as IBM, Apple, and Verizon to name a few. What does this mean to individual households? The Coalition Against Insurance Fraud (CAIF) estimates this fraud to cost approximately $950 per family.
The Insurance Information Institute (www.iii.org) has one of the best definitions of claims fraud:
?Insurance fraud is a deliberate deception perpetrated against or by an insurance company or agent for the purpose of financial gain. Fraud may be committed at different points in the insurance transaction by applicants for insurance, policyholders, third-party claimants or professionals who provide services to claimants. Insurance agents and company employees may also commit insurance fraud. Common frauds include ?padding,? or inflating actual claims, misrepresenting facts on an insurance?by I Want This”>application, submitting claims for injuries or damage that never occurred, and ?staging? accidents.
Insurance fraud may be classified as ?hard? or ?soft.? Hard fraud is a deliberate attempt either to stage or invent an accident, injury, theft, arson or other type of loss that would be covered under an insurance policy. Soft fraud, which is sometimes called opportunity fraud, occurs when a policyholder or claimant exaggerates a legitimate claim.
So getting a handle on fraud can be an overwhelming proposition as it happens in many different ways and the methods of committing fraud are also becoming more and more sophisticated. As a result, the methods to detect fraud or potential fraud need to also rise in the level of sophistication. It is no longer good enough to rely on just a claims score against structured data in our systems to create an alert for a potential case of fraud. Techniques need to also include investigating using more advanced predictive analytics, text mining of internal unstructured data and even the usage of natural language interpretation to also search into recordings, unstructured data sources in social media.
Read our next blog as we discuss the good bad and indifferent in these methods for detecting fraud…..