In the recent past, a New York City court convicted 13 people including six medical professionals who had, over several years, milked auto insurance companies of millions in fraudulent claims. How did the team of fraudsters manage this – by staging ‘fake’ accidents in rental cars and then ‘treating’ the alleged victims to a battery of unnecessary tests including expensive EKGs and MRIs.
The magnitude of insurance fraud today is startling, and it occurs wherever the insurance business is booked. Insurance fraud accounts for at least 10 percent of all insurance premiums, a percentage that has remained relatively constant over the past two decades. In reality, the entire scale of insurance fraud is unknown. Even if there were a single body charged with tracking all fraud, the task would be impossible, as the types of fraud are diverse and continually changing.
Auto fraud, too, is clearly on the rise in the U.S. The concern is that detection of auto fraud is already a challenge, and will only worsen for the following reasons:
A variety of integrated models and other solutions are necessary to arm insurance professionals with appropriate automated capabilities for fraud prevention, detection and management. Business rules can be combined with other detection methods such as anomaly detection, predictive modeling, and social network analysis for use in identifying suspicious applications, potentially fraudulent claims and other anomalies.
One way to trace likely fraud is by analyzing the information siloed in companies on a person’s claims history, payment of premiums and residential addresses. By using computing power and statistical tools, it is possible to analyze information in order to throw up trends or profiles of potential fraud. Unlike traditional approaches, an approach that deploys analytics will provide -
Frequently, fraud begins during the initial insurance application process. This “underwriting fraud” or “rate evasion” is the result of misrepresentation of facts that directly affect the rating. Individuals may underreport the mileage driven for an auto, claim only personal use for a commercial vehicle, fail to report previous claims, lie about their health history, or misrepresent the characteristics of their property. In the U.S. in 2009, rating errors resulted in USD 15.9 Billion in lost revenue for private-passenger auto premiums, an amount equal to about 10 percent of all insurer premiums for this line.
As an example, WNS has worked closely with a leading auto insurance company that wanted to minimize application-stage fraud by understanding the profiles of fake customers, identifying patterns, and putting in place a proactive early warning system to support their investigation and fraud management teams.
Using analytics, the company was able to improve the rate of genuine claims and significantly reduce costs associated with fraud claims investigation. Auto insurance fraud costs genuine consumers, companies and the economy at large. Combating fraud with a well-thought-out analytics plan will help insurance companies conduct their business efficiently, increase customer satisfaction and enhance their overall brand image.
Join the conversation
25 November 2021
Banking and Financial Services
01 February 2022
08 December 2021