How can AI bring back the human element to travel insurance fraud investigations?

Dynamic problems vs. manual solutions

Travel insurance fraud is a dynamic problem, with fraudsters constantly changing their tactics to avoid detection. Despite this, many insurers are tackling this growing issue using only manual tools – multiple databases, pivot tables and Excel spreadsheets – which are difficult to adapt to new scenarios.

This approach leaves insurers playing constant catch up with fraudsters, with investigators spending days manually looking into cases. In the current environment, some fraud is missed by insurers, while false positives are too frequent. Plus, when an insurance investigator does spot something suspicious, they often lack the data to prove their findings.

This situation was compounded by Covid-19, despite the significant reduction in international travel. According to the ABI, while the number of fraudulent travel claims fell by half in 2020, the value of these claims increased by two per cent to £1.8 million. In addition, the average claims value was the highest ever, the average totalling over £2,300.

So – as travel reboots and holidaymakers make their way abroad once more – it’s clear that insurers must modernise their back office to protect against the impending resurgence of travel insurance fraud. That’s where artificial intelligence (AI) and machine learning (ML) tools come in. These technologies enable insurers to create dynamic solutions to a dynamic problem. Here’s how.

How can AI help deliver better outcomes for travel insurance companies and consumers?

AI enables insurers to optimise employee time and resources. Usually, employees spend several days carrying out research. However, caseworkers can rely on AI to analyse relevant, contextualised data and generate alerts accordingly. This both increases the efficiency of insurance investigators and improves customer experience.

Consider the travel example again. Imagine you’re an investigator working with rudimentary, manual tools like pivot tables and Excel spreadsheets. You might spend hours assessing an airline’s booking and billing data before finding a customer that seems to be filing a suspiciously high number or high value of claims. Even after embarking on a lengthy investigation, you may well find that this ‘discrepancy’ can be attributed to the fact that the customer is a business traveller. They are having to hedge their bets by booking multiple simultaneous flights for speculative meetings. They took out insurance to account for the fact that some bookings may be cancelled. After all this research and investigation, it was a very time-consuming false alarm.

If a physician was at a conference or on holiday during a particular week, how could they possibly have completed several dozen travel health insurance-covered treatments each day?

The insurance investigator in this scenario is not to blame: they wasted significant resources chasing a dead end, but if this investigator had been equipped with AI-powered analytical tools, the same travel trends could have been processed and interpreted in minutes – rather than hours. What’s more, AI would have produced significantly fewer false alarms, enabling the investigator to dedicate their time to following up on genuine leads – which means even more time saved.

AI is also much better at uncovering trends or patterns that aren’t easily recognised by a human – revealing hidden fraud.

Take the example of a fraudulent claim made for medical or injury treatment abroad. It can prove very difficult to assess whether a claim is fraudulent - whether the treatment actually took place – or not. Noticing the fact that there has been a large number of claims laid out in similar ways, with doctors performing the same kinds of treatment in different countries, would be very hard to spot for a human sifting through thousands upon thousands of medical claims. However, AI can spot these trends and patterns in seconds across vast amounts of data.

What’s more, AI can process enormous amounts of publicly available data from the internet – forums, social

media, Google reviews and more. For instance, if a physician was at a conference or on holiday during a particular week, how could they possibly have completed several dozen travel health insurance-covered treatments each day?

Striking the right balance

AI can analyse data in a fraction of the time it takes a human analyst – and with a much higher degree of accuracy. However, travel insurance will always require a human element. Complex decisions made each day by insurers on behalf of holidaymakers and providers will always need human input.

With AI and human employees working in tandem, insurers can easily uncover fraudulent claims while handling the issue in a fair and professional manner – punishing fraudsters and providing a smooth journey for genuine customers. By optimising certain processes through smart solutions, insurance providers can ensure that their analysts and investigators go after the complexities that drive decision making and maximise outcomes.