Historically, special investigation units focused mostly on fraud within the claims process. With millions of dollars at stake in indemnity and expense payments, this focus makes sense. But advancements in fraud detection techniques like predictive analytics can be used earlier in the insurance life cycle to stop fraudulent activity even before a claim is filed.
The underwriting process is designed to properly classify risk and apply the correct price and conditions of an insurance policy to protect both the insurer and the policyholder. And in times of reduced investment income, turning an underwriting profit is more important than ever. But not every applicant is honest. Premium or underwriting fraud occurs when someone intentionally conceals or misrepresents information when obtaining insurance coverage.
Top-line growth is among the highest priorities for insurers today. Mobility and "ease of doing business" initiatives have resulted in insurance companies implementing "straight-through underwriting processing" projects. At a time when insurers are looking to cut expenses, this is often a recipe for disaster and has unfortunately resulted in increased application fraud risk. Fraudsters have become increasingly sophisticated in their methods. They are aware that insurance companies are under pressure to increase premium revenue and do not always check all the application details for completeness or accuracy.
This streamlined approach comes at an enormous cost. According to Quality Planning Corporation, underwriting rating errors caused by application misrepresentation and other factors have led to more than $16 billion in annual premium leakage in US private passenger auto insurance alone. How do you deal with underwriting fraud risk? Here are three key areas of intervention.
Point of sale
There are several different approaches that can be used to address fraud risk at the point of sale. Agents are the first line of defense in this area and often benefit from more robust training. But technology can also play a role. Data prefill, cross-referencing public records and real-time risk analytics can help address the threat. This becomes especially important in the online direct channel where there is no agent to help assess the risk, and immediate responses are necessary to support straight-through processing.
Life of policy
The point-of-sale focus is important and is the most common place to begin. It should be included in any underwriting fraud detection strategy. But it is not the only place to look. The reality is that change is constant. This extends to the everyday life and business of the insured. For example, in personal auto insurance, an insured might change jobs, resulting in driving many more miles each month or possibly using their car in conjunction with their work. New drivers may enter the household. Unreported accidents or infractions could occur. Certainly, some insureds may report these changes as they should. But others do not. At the time of renewal or when policy changes are requested, there is an opportunity to reevaluate fraud risk for the policy. With more data available from premium payment history, customer service transaction logs and other sources, advanced analytical models can more accurately predict potential misrepresentation.
If a loss does occur, there is still an opportunity to be on the lookout for underwriting fraud. In fact, the details of the claim itself may provide leads into potential policy misrepresentation. Astute adjusters or automated fraud detection solutions can help identify these scenarios. For example, in the commercial space, the details of a workers compensation claim may suggest that inaccurate information was provided about worker classifications that could warrant a premium audit.
Analysis suggests that a substantial proportion of claims fraud is perpetrated through illegally obtained policies. Hence insurance companies that can reduce underwriting fraud can significantly decrease the exposure to certain types of claims fraud as well. Stopping fraud at this stage saves investigation, claim adjudication, litigation and recovery expenses. The Coalition Against Insurance Fraud reports that while nearly 90% of insurers report using anti-fraud technology, less than half use it for non-claims functions such as underwriting fraud. That is an invitation to develop a competitive advantage by establishing a robust technology-based underwriting fraud detection program.
About the author: James Ruotolo is an insurance fraud technologist, thought leader and the principal for insurance fraud solutions at SAS. Connect with him on Twitter.