How to prevent claims fraud with document automation and authentication 

Preventing fraud is a constant battle for insurers – and claims are a prime target for deception. Moreover, fraud is now harder to spot because the supporting material for claims is increasingly in digital formats, which are easier to manipulate and falsify. Additionally, technology is pushing straight-through processing and automation to new levels, which means anomalies may be missed in the quest for greater speed.

Naturally, insurers and their clients both want swift resolutions when a claim is filed. However, speed must be balanced with stronger security because fraudsters are becoming more adept at exploiting the vulnerabilities of digitalisation and finding new ways to make false claims. So, if digital technology and document automation are both a business strength and a weakness, how can insurers maximise the benefits of digitalisation while reducing the risks?

The need to combine speed with security was the challenge solved by Fortiro, a fintech that began life as part of PwC Australia before being spun off to form a separate company with a platform called Protect. Fortiro’s clients are enterprise financial services firms and include major banks, insurers, payments companies and lenders.

“We’re a software company that’s focused on financial document verification,” says Fortiro’s CEO Sean Quagliani. “Financial information is often vulnerable to fraud, and proof of income is an important requirement across financial services – one that can be falsified to defraud banks and other financial service providers.”

As Quagliani goes on to say, financial document verification has an obvious appeal for insurers and life insurance is a clear use case as claims teams need to determine the veracity of income before authorising payouts. Manual checks are time-consuming and prone to human error, so insurers need a better way to quickly and accurately identify suspicious claims, based on the characteristics of the financial information provided. 

“Documents can be assessed on a wide range of things to determine authenticity," says Quagliani. "For example, are there strange fonts and spelling mistakes or is the layout unusual or poorly formatted?"

This ‘forensic view’ draws on a blend of technologies that can scan and analyse content in documents. They include artificial intelligence, optical character recognition, detailed image analysis, and natural language processing. Collectively, when harnessed for a specific task – in this case, to authenticate financial details via the Fortiro Protect platform – these technologies can help resolve claims quickly while enhancing security.

“By picking out the bad, the technology helps to accelerate the good,” says Quagliani. “Most people are doing the right thing, and with around 97% of the documents that we process, there's nothing suspicious about them. That means the vast majority of what’s put through can go faster because it doesn't need to be double-checked or slowed down from a document review perspective.”

Quagliani explains that the software can run more than 70 fraud checks, analysing document layout, content and digital construction. By using AI-based rules, claims assessors can profile everything from the way a document looks to the terminology that is used, right through to the metadata and a document’s digital history. 

“Assessors can deconstruct all the attributes of a document,” says Quagliani, “and identify patterns and fraud trends with a level of detail that’s not possible with manual processing. Each fraud indicator is associated with a risk score. If multiple fraud indicators are detected, the overall risk score increases.” 

The technology is proving its worth in the banking sector – primarily for high-volume credit card and mortgage sales – so Hannover Life Re of Australasia (HLRA) wanted to test its potential in the insurance world.

“We ran some proof-of-concept trials with direct life insurance claims,” says Amy Sworden, Head of Claims Operations at HLRA. “We tested with claims where fraud was known and where fraud was suspected."

"The technology flagged all the known fraud cases and identified why the suspicious ones were fraudulent. Moreover, it also spotted fraud where this hadn’t been suspected.”  

Sworden says the results are very promising for life insurance: The trials revealed a potential to reduce claims leakage where the technology had confirmed total permanent disability (TPD) and income protection (IP) claims fraud or highlighted probable fraud needing further investigation before a payout can be approved. In addition, having demonstrated that the technology can identify income fraud, Sworden says other insurance use cases are worth pursuing.

“Aside from financial analysis, the technology could be used to assess medical documents,” she says. “Doctors’ reports, blood tests, death certificates and other medical submissions could all benefit from this AI-enhanced analysis, and we plan to work with Fortiro to build out these applications.”

Because Hannover Re is a direct insurer in Australia as well as a reinsurer, it is implementing the technology in its own business. At the same time, on the reinsurance side, it is spreading the word and promoting the benefits for carriers. 

The strategic collaboration between Hannover Re and Fortiro has not only transformed claims assessment but also earned the prestigious 2023 Global Development Award from Protection Review. Protection Review, a leading authority on the UK’s health and protection insurance industry, recognises global advances made in life and health insurance. This new award category celebrated the collaborative efforts driven by the team at HLRA, acknowledging the transformative impact of Fortiro’s technology on claims strategies and fraud mitigation.