You could not make it up – but they did. Every five minutes a fraudulent insurance claim is uncovered

  • 107,000 fraudulent insurance claims worth £1.2 billion uncovered by insurers in 2019. That is a new scam uncovered every five minutes – 300 a day.
  • Frauds worth £3.3 million detected every day.
  • A bodybuilder, police officer and a trainee GP among the cheats exposed.

Straight-through-processing (STP) and Automation might be great for policy holders but, unfortunately, for the opportunistic and professional fraudster STP is also undeniably attractive. Just as data mastery and the judicious use of AI is promoted for insurers to tackle fraud so professional fraudsters can use the very same technology to confound counter fraud efforts.

Fraudsters look for chinks in the industry’s armour and exploits the weakest link.

  • Genuine online documents can be altered
  • Receipts falsified
  • Accounts adjusted.

As fast as a fraud team’s algorithms detect a pattern of fraud the fraudsters alter the modus operandi (MO) in anticipation. Fraudsters take advantage of the long and vulnerable tail of motor claims in which they can add false evidence. Infants in the car. New physical and emotional injuries. New passengers.

Insurers can find it increasingly difficult to be agile enough to stay ahead of this cycle and deploy systems that anticipate and identify this rapidly changing fraudulent behaviour.

Just as quickly as a new technology is deployed by insurers the fraudsters are applying human ingenuity and technology to beat the insurers at their own game and cheat the system.

Claimants themselves are an opportunity to generate additional criminal revenues by means of the Dark Web which powers a marketplace for criminally obtained personal information to identify and contact potential victims. Claimants are redirected to Claims Management Companies rather than insurers to further hide the evidence trail.

It is not just professional fraudsters that are the problem. There is too often a feeling that insurers are fair game to over-egg claims and gain a little more back in settlement. Whenever a new phone is launched there is a surge in ‘broken phones’. STP settlements on claims below, say £800/$960, paying out automatically to save claims handler cost is dangerous. With over 2million home claims processed globally 360Globalnet consistently finds a well-designed eFNOL process leads to 30% to 35% of customers voluntarily withdrawing claims as they see their story-telling exposed. A simple process of

  • a brief freeform text description
  • followed by next step of having to upload photographs
  • followed by request for video that will give context to the claim
  •  quickly exposes fraud and the claimant knows it.

Over 30% of the time for home insurance!

That still does not tackle the professional fraudster and techno-savvy claimant. What is the answer?

The solution is a combination of technology (particularly data), collaboration and the human intuition of skilled Fraud professionals in the insurer and specialist inspection companies. The gnarled experience, sceptical intuition and hard gained knowledge of those who have worked in the   fraud and understand human phycology and behaviour. The harmonisation of people and technology.

Tools that leverage databases like Synectics, world-class investigation companies like Robertsons and the perceptive skills of inhouse fraud teams. Tools to make better decisions, spot potential fraud and investigate more efficiently.

Collaboration, co-operation and partnerships

I hear you ask, “What about AI and NLP? Aren’t these the solution to combat fraud?”

AI, BOTS and NLP have their place of course but there are two key limitations to be aware of. The hint maybe in the term ‘artificial’.

The first limitation is in the data or, to be clearer, in the lack of accessible data. The second is the unpredictable nature of professional fraud.

Consider this question first. Would you rely on a Satnav unit in your car to guide you to an obscure part of London, Paris, or New York if it only accessed data on 20% of the roads? No, of course not!

Yet that is exactly the situation with insurers as most data is held in data sources that are hidden within the unstructured data of documents. The freeform comments, the many fields in claims forms, invoices, medical reports, investigation reports, solicitors letters, claims management company submissions, emails and a never-ending list.

This 80% of data is where professional fraudsters hide their devious claims outside the scope of inquisitive fraud inspectors unless they have the time to laboriously search through them manually. And they just do not have the time even if they knew what they were searching for as the fraudsters continuously change their modus operandi (MO) to escape the attention of the claims team and AI powered fraud software.

Any successful software must have the investigative skills and intuition of Sherlock Holmes, Commissaire Maigret and Hercule Poirot combined.  Coincidentally 360Retrieve has been deployed by police forces in the UK to deliver just that and is equally valuable for insurers.

Insurers can combine the enterprise fraud knowledge of its own professionals with that of specialist fraud investigation companies and 360Globalnet’s own intrepid fraud investigators. They can use 360Retrieve to apply intuition, hypotheses and existing fraud indicators and watch lists to search all 100% of the data with the comprehensive fraud tool kit. This continuous process enables them to create new fraud indicators rules and update watch lists and combine this output in comprehensive rules engines that categorise claims in the classic red, amber green (RAG) model.

Better still, as professional fraudsters change their MO, which they do all the time, the fraud team can spot and anticipate this. The outcome is to achieve returns on investment of between 12: 1 to 20:1.

This is because this combination of human intuition and technology is the ideal one to deal with behaviour that is neither repetitive nor predictable. If it were then AI solutions would be the natural choice. Professional fraudsters use technology and their own intuition to outsmart AI so you need the counter fraud tams to be able to outwit them.

Sherlock Holmes adds technology to his formidable talents to identify and tackle fraud as do the fraud professionals in the insurer. If you need any extra incentive to take this approach just look at these fraud statistics from US and UK studies.

The Fraudster Next Door: 30 Insurance Fraud Statistics

Published in Fortunly September 2020

Detected Insurance Fraud – ABI Report

September 2020