Insurance fraud is one of the oldest types of fraud known. The first recorded instance was way back in 300 B.C., when a Greek merchant intentionally sunk his cargo ship attempting to defraud a lender. It didn’t work out too well for this merchant. He drowned trying to escape the sinking ship. Fraud has been around since the beginning of commerce, and today, insurance fraud costs insurers (and society at large) billions of dollars a year.1
The insurance industry continues to make significant investments to develop new ways to combat fraudulent claims. As new and intricate ways are found to cheat insurers, claims adjusters must also find innovative ways to uncover it. One emerging approach insurers are taking is to scour social media sites for evidence of potential fraudulent activity by a claimant. Insurance fraud affects companies, customers, and economies across the globe, and companies that can find new detection tactics may be able to achieve a competitive advantage in the industry.
Over the last 15 years, social media has become almost omnipresent in society. What started as a fun new way to interact with friends and family around the world has exploded into a new marketplace, a new political arena, and a massive source of (sometimes publicly available) data. It’s also gone beyond being merely “social.” Nearly every company has a social media presence, and many industries make use of the various platforms, especially for marketing and branding. However, defining a target market and trying to hawk your wares to various demographic groups is far from the only way industries are taking advantage of the global obsession with social media networks.
The insurance industry is one of the industries taking its use of social media beyond marketing. Claims investigators for insurance companies might be found spending hours of their day on Facebook, Twitter, and various other social media platforms. To an average passerby, this might just look like a distracted employee procrastinating or even avoiding work. In actuality, this social media browsing could save the company from paying large fraudulent claims costs. Companies are realizing that social media is not only a great marketing tool, but also that it may also result in a considerable reduction in loss payments.
Social media is changing the way some insurance companies identify fraudulent claims. These claims are a larger issue than most people realize, and the financial effects are staggering. Each year, an estimated $80 billion is stolen by fraudulent claims across all insurance lines. To put this in perspective, an estimated $1 of every $10 paid in property and casualty insurance losses is on a fraudulent claim.2 Insurance fraud occurs when a claimant acts intentionally in order to receive an insurance benefit. Because insurance only covers unintentional losses and honest claims, these intentional acts (typically set out to appear accidental) are considered unlawful and fraudulent.
Fraudulent claims can arise in a wide assortment of “creative” ways across all insurance lines. Restaurant owners intentionally light their buildings on fire and flee the scene with hopes to receive compensation to build a new restaurant. Friends work together to stage car accidents to benefit from an auto insurance payout. Employees in all vocations receive workers' compensation benefits for either faking injuries or claiming the injury was work-related when it actually occurred on a weekend adventure. Children, spouses, or other family members murder their loved ones in order to receive payouts from life insurance policies. Ultimately, these claims result in an unjustified indemnity payment to a claimant who was only seeking the payment for personal gain.
Insurance fraud is becoming more and more of an issue. In 2010 through 2012, there was a 27% increase in suspected fraudulent insurance cases.3 As you may expect, the surge in fraudulent claims undoubtedly has an adverse impact on insurance companies. Losses for the company are higher because they are paying out more indemnity dollars as well as associated expense payments. Not only that, but there are also significant resources spent investigating and attempting to prevent fraud. All of this contributes to costs insurers would not have to bear in the absence of fraud. As a result of these costs, the insurance companies are less profitable and may even be at risk for insolvency.
To compensate for increased loss and expense payments, the insurance companies must increase their cash inflows. This means increased rates, resulting in higher premium payments for policyholders. Honest customers who seek insurance products for lawful reasons ultimately suffer through these higher premiums. The estimated increase in premium to a typical U.S. family each year is between $400 and $700.4 There are also indirect costs because insured businesses must charge consumers a higher price to account for their own increased premium expenses. When used honestly, insurance companies pool premium dollars to help the insureds who file a claim. Fraudulent claims unfairly take resources from honest customers, and insurance companies must be active in protecting their customers.
It is clear that fraudulent activity is an issue that needs to be addressed, but is social media investigation really the best (or even a worthwhile) approach to doing so?
With the immensely high rate of social media usage, some insurance companies are turning to this large source of public information to help combat insurance fraud. As of April 2016, there are 1.59 billion active Facebook users every month globally, while 400 million people use Instagram every month and 320 million users are active on a Twitter account monthly.5 Social media users account for a substantial portion of the population, and these users are generating a massive amount of data, an insurance company’s best friend.
Each day, 500 million tweets are posted—about 6,000 tweets a second.6 As of May 2013, 4.75 billion pieces of content were shared daily on Facebook. Currently, every 60 seconds on Facebook, 510 comments are posted, 293,000 statuses are updated, and 136,000 photos are uploaded.7 Unless social media users have adjusted the privacy settings on their accounts, all information that is posted is considered public. This means that insurance companies have free access to any non-private posts from their customers (or anyone else for that matter). The insurance industry thrives off of data for business purposes such as underwriting, and now, this social media “data” may help insurance companies succeed in combating insurance fraud.
There are many success stories of investigators who were able to uncover fraudulent claims by perusing social media. For example, one woman claimed to have lost her wedding rings in the ocean, but investigators found a picture on social media where she was wearing her “lost” wedding rings. Another man tried to receive a payment from his auto company for an accident. However, upon investigation, the company found a video online captured by a bystander of the “accident.” The video showed the owner intentionally drive his car into water without any attempt to manage the severity of the situation.8
Other things investigators are on the lookout for include social media connections between multiple parties involved in the claim, changes in job titles when an insured is receiving disability benefits, or older posts trying to sell something that has now conveniently been damaged in an accident. Indications like these point out the possibility of fraud, and, when confronted, claimants will often immediately admit to their fraudulent behavior. The pictures, posts, and videos found on social media often serve as evidence that is too concrete to deny.
While insurance companies are occasionally lucky enough to uncover evidence about fraudulent situations with social media, the reality is that doing this type of time consuming investigation on all claims filed is not only unrealistic, but also costly. In hopes of providing excellent customer service, insurance companies often try to pay an insured quickly after a claim is made. With many claims filed daily, any form of lengthy investigation can prove to be a bottleneck of the process. In addition, an analysis performed by KPMG revealed that general fraud in North America is most frequently discovered by accident or through tip-offs, management review, or internal audit.9 If most fraud discoveries are a result of this rather inefficient process (or even dumb luck), could a more efficient process transform fraud detection?
While analyzing social media can occasionally result in a big win in the fight against insurance fraud, the costs will not always outweigh the benefits. However, if paired with data analytics, the likelihood of uncovering fraudulent claims can greatly increase for a company. Data analytics gives a company the opportunity to process large amounts of data and quickly identify important outliers or other potential indicators of fraud.
For example, geospatial analysis can be utilized when looking for fraud in wind, hail, or flood damage claims. This statistical analysis helps identify what geographical locations were most affected by a storm and where the company would expect to receive claims. It could also aid in identifying the likely severity of a claim based on the proximity to a storm event. Receiving a claim from outside the affected area or a very large claim from a minimally affected area should trigger the need for further investigation.
Analysts can also examine historical claims to identify typical frequencies and severities of policyholder claims. When a current period's claims are compared to historical data, one can identify cohorts of policyholders who are either making more frequent claims or claims with higher loss amounts. Investigators may want to look further into these types of policyholders to look for further signs of possible fraud.
As is the case with any emerging technology, its use is not restricted to a single party. Fraudsters are aware of the benefits of using technology as 24% of fraud cases analyzed worldwide showed that technology “significantly enabled” the fraudulent behavior. Claims adjusters, on the other hand, seem to be a bit behind the trend as only 3% of fraud worldwide was detected using data analytics. By monitoring for unusual behavior more consistently, these companies will be in a better position to uncover fraud.10
Data analytics can be largely beneficial as it can quickly narrow a large pool of claims by flagging the potential fraudulent ones. However, because of the intricate nature of insurance fraud, data analytics will not necessarily provide evidence for a fraudulent claim. A balance between analytics and a more qualitative type of investigation may be most advantageous.
Insurance fraud is a significant issue with staggering financial impacts. Taking a purely analytical or qualitative approach to fraud investigation may not be very beneficial for insurance companies. The large number of claims received does not allow for individual investigation. This is where data analytics can be beneficial because it sorts through large amounts of data to flag potential fraudulent claims. However, analytics alone will not provide investigators with enough evidence to prove fraud. From here, the investigator could turn to a more qualitative approach, such as social media investigation, which will present an opportunity for more material evidence that can prove fraudulent behavior. Companies must be strategic and proactive in uncovering fraud in order to protect themselves and their honest customers.