Dynamic problems vs. manual solutions
Travel insurance fraud is a dynamic problem, with fraudsters constantly changing tactics to avoid detection. Despite this, many insurers are tackling this growing problem with only manual tools — multiple databases, pivot tables, and Excel spreadsheets — that are difficult to adapt to new scenarios.
This approach leaves insurers constantly tracking scammers, while investigators spend days manually investigating cases. In the current environment, insurers overlook some of the fraud while false positives are too common. Also, when an insurance investigator discovers something suspicious, they often lack the data to back up their findings.
This situation has been exacerbated by Covid-19 despite the significant drop in international travel. According to ABI, while the number of fraudulent travel claims fell by half in 2020, the value of those claims rose by two per cent to £1.8million. In addition, the average claim value was the highest ever at over £2,300.
As travel restarts and vacationers head abroad again, it’s clear that insurers need to modernize their back office to protect against the imminent resurgence of travel insurance fraud. This is where artificial intelligence (AI) and machine learning (ML) tools come into play. 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 optimize employee time and resources. As a rule, employees spend several days doing research. However, case workers can rely on AI to analyze relevant, contextualized data and generate appropriate alerts. This increases both the efficiency of insurance investigators and the customer experience.
Look again at the travel example. Imagine you are an investigator working with rudimentary, manual tools like pivot tables and Excel spreadsheets. You may spend hours reviewing an airline’s booking and billing information before finding a customer filing a suspiciously high number or value of claims. Even after a lengthy investigation, you may find that this “discrepancy” is due to the customer being a business traveler. They need to hedge their bets by booking multiple simultaneous flights for speculative meetings. They have taken out insurance to cover the fact that some bookings may be cancelled. After all that research and investigation, it was a very time consuming false alarm.
If a doctor was at a conference or on vacation in a given week, how could he be completing dozens of travel medical consultations a day?
The insurance investigator in this scenario is not to blame: he wasted significant resources chasing down a dead end, but had that investigator been armed with AI-powered analytics tools, the same travel trends could have been processed and interpreted in minutes—rather than hours. In addition, the AI would have produced significantly fewer false positives, allowing the investigator to focus his time following up real leads—which means even more time savings.
AI is also much better at uncovering trends or patterns that aren’t easily spotted by a human — and uncovering hidden fraud.
Take the example of a fraudulent claim 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 are a large number of claims designed in a similar way, with doctors in different countries performing the same types of treatments, would be very difficult for a human going through thousands upon thousands of medical claims recognize. However, AI can spot these trends and patterns in a matter of seconds in vast amounts of data.
In addition, AI can process enormous amounts of publicly available data from the Internet – forums, social networks
Media, Google Reviews and more. For example, if a doctor was at a conference or on vacation in a given week, how could he complete several dozen travel medical consultations a day?
Find the right balance
AI can analyze data in a fraction of the time it takes a human analyst – and with a much higher level of accuracy. However, travel insurance always requires a human component. Complex decisions that insurers make every day on behalf of travelers and suppliers always require human input.
With AI and human agents working together, insurers can easily uncover fraudulent claims while dealing with the issue fairly and professionally – penalizing fraudsters and providing a seamless experience for real customers. By streamlining specific processes with intelligent solutions, insurance providers can ensure their analysts and investigators address the complexities that drive decision making and maximize outcomes.