Welsh police have done an incredible job in breaking a car insurance fraud ring in South Wales where a crash for cash swindle made a gang up to £2m – but such fraudulent operations will go undetected if the British insurance industry does not escalate its detection capabilities, according to Emil Eifrem, pictured, of Neo Technology.
A criminal gang in South Wales were recently caught as part of a huge ‘crash for cash’ style insurance scam, faking car crashes and injuries that is believed to have netted them up to £2m. Run from a family garage in South Wales, the bogus insurance and compensation operation numbered 81 people, making the scheme one of the largest insurance frauds in British legal history. Regular payments were creamed off by the network of conspirators – for sums of anything from a few thousand to £40,000.
The gang led by the Yandell family was eventually caught following a highly complex and lengthy police investigation. Investigations first started in 2011, following a series of car and motorcycle thefts in the Welsh valleys. The police became suspicious when they found CCTV footage as part of their enquiry, which showed a Land Rover being deliberately destroyed by a forklift truck. The perpetrators were eventually first brought to court in 2013. Sentencing was given out in January of this year.
Gangs like the Yandells are not unusual. Fake road accident claims and insurance frauds are ongoing. They cost insurance companies hundreds of thousands of pounds and push up insurance premiums for motorists.
A stolen car incident lead the police to Yandell’s garage. Posting incriminating evidence online enabled the police to nail the gang. But the investigation, dubbed operation Dino, was a complex one. The truth is insurance companies are relying on outdated technology in a bid to protect themselves from fraudsters. Standard relational databases are used in most insurance firms today to spot fraud. Relational databases work for discrete data, but they have not been designed to deal with the bigger network of relationships that feed the fraudulent business of ‘crash for cash’.
IT analyst group Gartner cautions, “[We] don’t consider traditional technology adequate to keep up with criminal trends.” .
The answer is to use technology that can recognise new fraud patterns in real time. This technology exists today and is known as the graph database, developed to work with data at scale by manipulating the patterns in it. Paypal, for example, is using graph technology to perform fraud detection in real time. Graph database technology, however, isn’t just open to the big players. An increasing number of small to medium enterprises are also fast seeing the value of the technology. Forrester Research estimates that more than one in four enterprises will be using such technology by 2017, for instance .
Exploring the way people are connected can’t be achieved with just records or tables. To uncover a ‘cash for crash’ ring requires a number of tables in a complex schema such as alleged Accidents, Vehicles, Owners, Drivers, Passengers, Pedestrians, Witnesses, Providers, joining these together multiple times — once per potential role — in order to see the full picture. As these operations can be both costly and computer power hungry, especially for large data sets, this analysis is often ignored with conventional relational databases.
Discovering fraud rings with a graph database is far easier in technical terms. This is because graph databases are designed specifically to query intricate connected networks searching for fraud patterns, so they can be used to identify fraud rings. It makes sense for this approach to be used in insurance company’s standard checks at key points in a claim’s trail, such as when it is filed, to flag up suspected fraud rings in real time.
‘Cash for crash fraud’ has become a serious issue for the insurance industry, with the Association of British Insurers (ABI) estimating that deceptive claims add an extra £50 to premiums annually.
Insurance companies need to up their arsenal against fraud rings, who are getting more and more sophisticated. By adopting tools like graph databases they can start to win the war against fraudsters and consumers will finally be able to see an end of premium hikes.
The author is co-founder and CEO of Neo Technology, the company behind the Neo4j graph database (http://neo4j.com/).
