How technology is defeating Cash-for-Crash scams, and other industry revelations
by Emil Eifrem
Mr. Eifrem is co-founder and CEO of Neo Technology, the company behind Neo4j, the world’s leading graph database. Visit here.Fraud rings are big business. Recently police in the United Kingdom managed to break an insurance fraud scam, but such crimes continue to go undetected and will only be addressed if the insurance industry dramatically improves its powers of discovery.
Recently a criminal gang in Blackwood, a former mining town in the United Kingdom, was caught in a cash-for-crash scam that was estimated to be worth as much as $2.6 million dollars.
The gang was caught via a complex police investigation that exposed one of the biggest organized motor insurance fraud crime rings the UK has seen. The Yandell family honed their expertise in running up large auto insurance claims built around exaggerated or completely fictitious motor vehicle collisions together with related personal “injuries”.
Regular payments were piped off by a network of 80 conspirators for sums ranging from a few thousand dollars to $50,000. Police believe the fraud ring may be much larger, but others have yet to be prosecuted.
Not all that clever…
How did this audacious crime go on for so long? The fraudsters were not using clever tactics. In many ways it was very simplistic. But one thing the criminal ring did know is that soft tissue injuries are easy to falsify and difficult to prove such as sore backs or whiplash. With the help of doctors, lawyers, and even auto body shops to stage vehicle bodywork damage the Yandells’ family thought they were invincible.
Around 21 percent of bodily-injury (BI) claims and 18 percent of personal injury protection (PIP) claims closed with payment had the appearance of fraud and/or buildup, according to the Coalition Against Insurance Fraud. Buildup involves inflating otherwise legitimate claims.
Staging fake accidents and injuries is nothing new. A favorite trick of fraudsters is to manage crime rings by reusing participants in escapades. In other words, an accident may have a person play the part of the vehicle driver. In another they may play the role of the witness – and so the story chain continues. In many ways, it comes down to knowing where to look.
Relationships play an important role in cash-for-crash crimes. Inventive use of identities can be used to set up any number of fake accidents, even with a small group of criminals. This, just like the Yandells’ ring, can be a very profitable scam.
A more fortuitous accident…
All this seems very straightforward until you dig a little deeper and realize that the shocking aspect of this story is that they were caught by complete accident. If the authorities hadn’t stumbled on their scam they could have gone on for years without detection. All it took to trip them up was a sharp-eyed law enforcement officer to spot a piece of paper with a handwritten script on what to say to the insurance company.
Also linked to this story is the use of social media. As soon as the investigation was launched the police assigned resources to track the Yandells family on Facebook and find who they were connected to. Police detectives shadowed the gang on Facebook and social media and came up with some important links. But the lesson to be learnt from this is that conventional ways of uncovering insurance fraud are just not adequate.
Insurance companies are depending on outmoded technology. Standard relational databases, for example, are still used by insurance companies in a bid to spot potential fraud. Relational databases work well for discrete data, but they do not have the capabilities to deal with large network of relationships that sit behind the cash-for-crash “industry”.
Standard approaches are not reeling in fraudsters…
IT analyst group Gartner, which tracks different types of fraud, agrees that a new investigatory platform is required. “[We] don’t consider traditional technology adequate to keep up with criminal trends.” , the firm said.
The answer is a solution that can spot fraud patterns in real time. Graph database technology fits the bill because it was created to work with data at scale and manipulate and pull out patterns in it.
It is impossible to explore and expose the way people are connected via records and tables.
To discover a cash-for-crash fraud ring requires a number of tables in a complex schema such as: Accidents, Vehicles, Owners, Drivers, Passengers, Pedestrians, Witnesses, Providers. Then, all of these tables would need to be joined together multiple times — once per potential role — in order to get a full picture. This is complex, time consuming and expensive for large datasets, so it is little wonder it is often ignored.
Technically, however, spotting fraud rings using graph databases is much easier. Why? Because they are developed to query intricate connected networks, so they can be used to identify fraud rings like the Yandells’ without having to overcome complex technical challenges.
This is why a graph database approach should be added to every insurance company’s standard checks at appropriate touch points, such as when the claim is filed, to flag up any suspicious circumstances.
Graph databases are a new way of looking at the relationships between data points that is proving highly effective at spotting the hidden connections between what may appear like regular customers and whether any dishonest plans are afoot. Many experts believe graphs may be the ultimate way to work with the complexity of Internet and social data to do just this, in fact.
Insurance fraud is costing us all at the end of the day. The FBI estimates the total cost of insurance fraud (non-health insurance) to be more than $40 billion per year. That means insurance fraud costs the average U.S. family between $400 and $700 per year in the form of increased premiums.
Without tools like graph databases, fraud rings will continue to feed off the insurance industry, resulting in higher premiums to the consumer. Insurance companies need to act now before the fraudsters get the upper hand.
