Tag Archives: insurance fraud

Innovation in Fraud-Detection Systems

In a world of straight-through-processing and “touchless” claims, customers are demanding faster pay-outs on their insurance claims through smarter, more intuitive digital interactions and customer-centric support models.

Until fairly recently, standard industry processes have allowed time for loss adjustors, claims handlers and expert SIU investigators to appropriately assess customer claims. This approach has been a largely effective, but resource-intensive control on fraud. However, with the introduction of increasing automation, there is far less time available now for human review.

Insurers want to keep customers happy with smooth and rapid processes, but they also want to be confident that they are paying the right people, in the right circumstances, and limiting the opportunity for fraud. To achieve both of these objectives, real-time risk detection technology has a crucial role to play.

The far-reaching impacts of fraud

Insurance fraud has too often been regarded as a victimless crime. The reality is very different. Fraud has an immense impact on society, seriously damaging trust as well as creating material financial implications. According to the Coalition Against Insurance Fraud, criminals steal at least $80 billion every year from American consumers. Premiums rise to manage this additional risk, affecting all customers. Fraud also hurts loss ratios, disrupts daily operations, distorts pricing and affects reserves calculations.

And it’s not just insurance companies that pay when criminals carry out fraud—innocent people, often customers, get caught up in these crimes more often than most would like to think. Arson, murder-for-hire, crash-for-cash, staged accidents and medical malpractice are all examples where organized crime groups have targeted innocent citizens and exposed them to physical harm.

With insurance processes digitizing at an increased rate, the opportunity for fraud has expanded significantly, and it is vital that appropriate responses to those threats are available.

See also: It’s Time for Next Phase of Innovation

Demand more from technology 

Anti-fraud technology has already evolved at an exceptional rate in the last five years, which has included the creation of better investigation tools and experimentation with data science or machine learning techniques  But insurers should not accept yesterday’s technology when they can be pushing for tomorrow’s:

  • Scoring and alerting should be available in real time to keep pace with the demands from automated claims management workflows.
  • Analytics should be transparent and explainable so that the work and decisions of investigators are defensible.
  • Technology should be built on open architecture, should be capable of integration with core claims management or underwriting systems in real time and should offer flexibility for deployment in the cloud or on-premise.
  • Expert investigators and skilled data scientists should be able to focus on the highest-value cases rather than being frustrated by mundane data tasks.
  • Software and systems should support processes where appropriate, but insurers should be able to independently own and manage their own analytics without relying on external services.

Many companies find themselves working with siloed data, attempting to catch irregularities across unconnected data sets. Instead, insurers should demand a single view of all parties—policyholders, claimants, suppliers, brokers—to work within a single data set.

Insurers should also be able to use fraud management technology to easily detect and manage instances of identity manipulation—the slightest change between a name, date of birth, ID or address should be easily spotted and flagged, even if it’s across multiple data sets, to root out fraud without delay. Detection should also consider the relationships between parties, which is often as crucial to understand as the circumstances of each individual claim.

Data privacy regulation has changed significantly in the last decade with the introduction of new laws such as the California Consumer Privacy Act or GDPR in the EU. To ensure compliance. security models must be sufficiently granular and be able to support different user types in accessing different levels of data according to their specific permissions.

Finally, rather than opting for point detection solutions, analytics capabilities should be applied to deliver value across the enterprise. For example, intelligence that can be gained from a claims fraud detection solution can be highly valuable for detecting and preventing underwriting fraud. The same intelligence can equally be helpful in identifying churn risk or upselling opportunities. The technologies being deployed for fraud should also be sufficiently scalable and robust to service multiple use cases to maximize value and achieve a far lower overall cost of ownership.

See also: 7 ‘Laws of Zero’ Will Shape Future

Customers want to associate their insurers with stability, trust, competence and airtight operations. With so much innovation happening globally, now is the moment for insurers to think big and evolve their enterprise fraud capabilities. Fraud is not a victimless crime, it is not the cost of doing business and we do not have to accept the status quo.

What’s New in Fight Against Fraud?

Insurance fraud has been around since, well, the beginning of insurance.

The ancient Greeks created a form of maritime insurance to indemnify against potential losses incurred with the sinking of a commercial ship in transit. It became a common scheme for the boat owner to hide the boat in a foreign port and collect the insurance money. Even in those early times, special investigators were hired to determine if the boat had indeed sunk.

Fast-forward to the present, and, for the last few decades, the industry has been using increasingly sophisticated technology to address fraud. Now, several technologies can change the game for detection.

For example, machine learning, social media and aerial imagery can all contribute. All generate and rely on massive amounts of data, including many new data sources. Whether we are talking about opportunistic fraud or organized crime rings – these technology areas provide terrific opportunities to combat fraud.

Of course, fraud may occur during the underwriting OR the claims process. When a person or business is applying for insurance, there is always the potential to purposely supply incorrect information to get a lower rate. On the claims side, fraud may occur at many points during the lifecycle. In the case of staged accidents, it is occurring even before the accident occurs.

So how is the advance of technology aiding in fraud detection today? First, let’s look at new data sources.

Rate evasion can be more easily spotted today due to the wide variety of new data sources that can provide checks on the information provided by a customer or agent. For example, for auto, it is easier to spot true garaging locations or identify if a vehicle has been in a flood. For property, there is a wealth of data about the current characteristics of the property.

See also: Identifying Fraud in Workers’ Comp  

When it comes to machine learning, big data approaches with massive computing power and huge data sets can spot patterns and anomalies that it would be impossible for humans to spot – and do so with a lower rate of false positives. Social media has become a central tool for investigators and law enforcement, especially for workers’ comp fraud. We’ve all heard stories about individuals claiming disabling injuries then show up in Instagram pictures skiing or skydiving. The social media universe also yields a lot of information about connections between various individuals and businesses that can be mapped to identify fraud rings. Using aerial imagery, it becomes easier to compare before and after pictures of a property to determine if damage was caused by a particular weather event.

One of the biggest benefits of all this new capability is that technology allows fraud to be detected significantly earlier in a claim and with greater accuracy, so that Special Investigative Units (SIUs) and claims processes are more effective (compared with before, when SIUs or management found out about a fraud three to four weeks or longer after FNOL, by which point it was too late).

There is still much work to be done to find the right solution partners, integrate new solutions with existing systems and determine the optimum balance of technology and human expertise. But there is now greater potential to finally make significant headway in reducing fraud, especially the potential for earlier identification and more accurate outcomes. That’s what’s new and encouraging in this long-running battle!

Fighting Fraud With Data Analytics

The FBI reports that the total cost of insurance fraud is estimated to be more than $40 billion per year, costing the average U.S. family – in the form of increased premiums – between $400 and $700. A long-established and growing problem, insurance fraud has its many guises – ranging from tiny, one-off opportunistic cases to multimillion-dollar syndicates of customers and suppliers working together to routinely defraud insurers.

Luckily, digital enhancements within the insurance industry have been able to help companies lessen certain fraud risks – particularly when data analytics is brought into the mix.

To remedy insurance fraud using data analytics, individuals and businesses must be analyzed as they exist in the real world – as holistic, connected entities. To make these kinds of connections accurately, detection strategies must process high volumes of data in real time, be able to generate and constantly update a view of entities and apply a scoring model to the full picture. This allows companies to track and catch fraud, even across insurance lines and when multiple people are involved.

Fortunately, there are now technologies that are able to do just that – detect fraud and understand risk throughout a customer’s lifecycle. This will, in the long run, provide better claims processing and a healthier insurance system.

See also: Leveraging Data Science for Impact  

Quantexa, a data analytics firm that uses AI technology to piece together suspicious customer behavior, enables companies to make better decisions with their data. Their technology allows users to knit together vast and disparate data sets and derive actionable intelligence, a task that would normally take a human many months to complete. This technology can be focused on a single person and the many data points that are correlated to him or her, or larger entities such as corporations.

Technology like that of Quantexa’s can gather both claims and policies and build a network that provides three levels to which one can apply analysis:

The claim: This analyzes claim behavior over a long period. For instance, has a person filed for soft tissue damage multiple times? If so, how often and at what rate? This frequency could be a marker for fraud. There is also the ability to review if claims are filed close to when policies are taken out – another marker for fraud.

The entity: The entity can be either a claimant or, say, a medical provider; the analysis lies within the relationship between the two entities. Believe it or not, there are instances where medical providers have intentionally and habitually provided the wrong injury code; for example, if a claimant is in the hospital for an injured leg, the medical provider bills the insurance company for a more expensive procedure, such as a hysterectomy. Technology can detect and assess injury code discrepancies.

The network: This is based on the density of relationships and connections between claimants, witnesses, medical providers and beyond, and can stem from both claim information and transactional data. For instance, are multiple claims from “different” claimants all going to the same bank account? Factors can be pieced together to paint a larger picture on where fraud is originating.

See also: How Connected Data Can Help Stop Fraud  

Technology allows fraud to be detected much earlier on and across much larger schemes than humans ever could – a fact that should give thieves something to be concerned about, and all honest insurance policyholders something to rejoice about.

How Insurance Can Exploit Blockchain

As the insurance industry races to adopt new technologies and stay one step ahead of the insurtech disruptors, blockchain has become a widely discussed topic. With use cases in fraud protection, risk management, claim processing and smart contracts, blockchain has a promising future with benefits for both independent agents and carriers. Although adoption is still in its initial inception, interesting pilot use cases are popping up across the industry.

Blockchain’s greatest value lies in its distributed ledger technology, which acts as a uniform source of truth. This technology is very hard to hack and provides a wealth of benefits to every member of the insurance distribution channel. Let’s take a look at some of the ways blockchain is being used in insurance today.

Smart Contracts

In my experience and research, the most commonly discussed use case of blockchain lies in the execution of smart contracts. For those unfamiliar with the concept, blockchain’s distributed ledger allows one computer to register an outgoing transaction and then enables a peer group of computers to validate and accept the transaction through a consensus-driven approach. This means that copies of the transactions are now stored in a distributed fashion across the network, and hacking or altering this information will require more than 50% of the computers in the network to be compromised simultaneously. This ensures that the source of truth is preserved and protected in a robust fashion and can be accessed by any legitimate party with the right permission levels.

While the execution of smart contracts in travel insurance has already made a splash – see AXA or FlightDelay or Lemonade – there remain other use cases that are sure to make a large impact. One example is flood insurance. In areas prone to heavy rainfall and flash floods, insurers can use regional geological data to automatically trigger insurance claims. Meaning, once flood waters reach a predetermined level, a smart contract trigger will spontaneously file a claim for the insured. Another application with a similar process is earthquake insurance. If an earthquake were to occur above a certain magnitude, the smart contract would initiate the insured’s claim based on regional geological data and preset factors in the contract.

See also: Collaborating for a Better Blockchain  

I also see blockchain expanding into the auto insurance space through the use of telematics devices. These devices are already able to track data in terms of wear and tear, collisions and driving patterns. Such data can be used to calculate insurance premiums that are more targeted and personalized. In a broader sense, IoT-based sensor data can power the metered insurance space in the shared economy (Uberization).

For both the insurer and the insured, the smart contracts built on the blockchain will drive more efficiency across the insurance value chain. A key factor in the expansion and adoption of smart contracts in the insurance industry is data. Smart contracts are only viable if there are external sources of data that are validated and reliable. The more data that is universally shared and available, the more innovative insurance products will be adopted.

Fraud Protection and Proof of Insurance

The FBI estimates the U.S. government spends more than $40 billion per year on insurance fraud, leading to my next, and possibly most compelling, application of blockchain. With an aggregated repository of data that is validated and maintained by carriers, agents and government entities, it becomes easy to track down insurance fraud spanning multiple carriers. IBM has already announced a new framework for securely operating blockchain networks to directly fight insurance fraud, and I expect more companies to follow suit.

In addition to fraud protection, blockchain technology is powering another compliance innovation: proof of insurance. In December 2017, a consortium of insurance leaders dubbed the RiskBlock Alliance launched RiskBlock, a proof-of-insurance tool built on the blockchain framework. It was designed to help insurers, insureds and law enforcement simplify how they verify insurance coverage in real time, eliminating the need for paper-based insurance cards. Nationwide is already in the pilot stage with RiskBlock and hopes to expand the program this year.

Insurance Distribution Model

Despite new insurtech entrants disrupting the industry every day, innovations such as blockchain ensure that the insurance agent will always remain the cornerstone of the insurance distribution model. As reported in the examples above, the common theme among the benefits of blockchain’s distributed ledger technology — the ability to automatically file claims, process data and inform policies — drives efficiency and visibility into the entire insurance ecosystem. For carriers, a uniform and validated data source allows transparency into risk assessment, underwriting and a channel to reach the end-insured directly. With automated processes executed through blockchain, brokers are able to focus on building relationships, expanding their offerings and solidifying their role in the distribution model. Similarly, customers benefit from personalized and increased touch points, leading to better tailored insurance policies and cost efficiencies. As these relationships grow, so does the velocity of business…it’s a win-win for all the constituents in the value chain.

See also: Blockchain: What’s the Real Story?  

We are only just beginning to see the potential of blockchain technology in insurance. With blockchain and insurtech startups, coalitions such as RiskBlock Alliance and major carriers leading the charge, the insurance industry is poised for an imminent digital revolution.

Draining the Swamp of Insurance Fraud

An agent received the following email from a customer:

“A few people are telling me to save money on car insurance by NOT telling the insurance company who is driving my cars. I have a 23- and 16-year-old – the older one had two accidents, but her premium is reasonable at $2,300 per year for good coverage. These people are telling me that the cars are covered no matter who is driving so don’t tell them about your kids.”

These “people” are allegedly other agents bidding on her personal lines account. I don’t know about you, but I call this email insurance fraud. I suspect most regulators and state attorney generals would concur. For example, here is just one of many fraud statutes from Florida:

817.236 False and fraudulent motor vehicle insurance application:  Any person who, with intent to injure, defraud, or deceive any motor vehicle insurer, including any statutorily created underwriting association or pool of motor vehicle insurers, presents or causes to be presented any written application, or written statement in support thereof, for motor vehicle insurance knowing that the application or statement contains any false, incomplete, or misleading information concerning any fact or matter material to the application commits a felony of the third degree, punishable as provided in s. 775.082, s. 775.083, or s. 775.084.

See also: How Bad Is Insurance Fraud Really?  

A felony conviction is not an inconsequential thing, nor are the civil penalties and possible incarceration associated with insurance fraud laws. In addition to the fact that insurance fraud is illegal in every state, those that have adopted the NAIC’s Insurance Fraud Prevention Model Act or their own version of that law make reporting of such fraud mandatory. For example, the model act says:

“A person engaged in the business of insurance having knowledge or a reasonable belief that a fraudulent insurance act is being, will be or has been committed shall provide to the commissioner the information required by, and in a manner prescribed by, the commissioner.”

The industry and state regulators encourage the reporting of insurance fraud. States with mandatory reporting requirements usually have mechanisms for confidentiality and immunity. If you’re an agent who is aware of this market conduct, have you reported it? If you’re an underwriter or adjuster who is aware of an agent who has engaged in this practice, have you reported it in addition to terminating the agent?

In my blog, I often give “big data” a hard time, but this is an example of how it can supplement underwriting and claims. In a recent blog post, I expressed my distaste when my personal lines carrier sent me an additional auto insurance bill for almost $600 because it apparently learned that my son, who moved out three years ago, still gets his vehicle registration renewal mailed to our house. The presumption, without verification from us, was that he still lives here.

I don’t have a problem with this practice, just with the execution and presumption (from my viewpoint) that I’m dishonest. There is nothing wrong with verifying information provided by an insured or agent, and ‘big data,” without misplaced overreliance, can be a viable tool for that purpose. This is one reason why an agent who engages in the fraudulent behavior described above is being foolhardy. With the growth of data analytics, more and more agents are going to get caught engaging in this type of fraud. And I hope that carriers will have the backbone to report them and get them out of the business.

See also: 3 Major Areas of Opportunity  

This is not a singular or unique tale. I’ve heard it from agents before. Too many agents compete unethically, and some do it illegally. Whether it’s the personal lines agent deliberately underinsuring a home with a “guaranteed replacement cost” provision or the commercial lines agent undervaluing property insured on a blanket basis without a margin clause, the offender needs to be reported and driven out of the insurance industry.

Are you willing to do your part in cleaning up the insurance fraud swamp?