Practical Applications for Machine Learning in Claims – Anti-Fraud
Greg Firestone, Vice President of Data Science at Allstate Insurance, explained in a recent interview why his company began leveraging anti-fraud technologies to mitigate fraudulent claims. “It’s very hard to measure sometimes, but it’s happening,” Firestone said. “The best prevention is really being aggressive: using AI and data to find fraud. Data is your friend in this regard. Fraud is a problem that impacts all insurance companies, and we need to focus on it and make sure the fraudsters realise that we’re not easy marks.”
According to a VentureBeat report, the Firestone uses an AI-based solution to monitor and flag suspicious claims. Large insurance companies process thousands of claims daily, making it impossible for a team of human analysts to thoroughly review each instance for fraudulent activity. Thus, many insurance companies are leveraging advanced AI systems to automate this process, which allows them to reserve their teams for claims the AI-based solution has flagged as suspicious. Not everything can be done by robots, however. This particular insurance carrier understands that keeping an eye on future fraud trends will continue to require a human touch.
DOCOsoft – Insightful InsurTech
DOCOsoft – a builder of intelligent software systems for big-ticket insurers – helps insurers and reinsurers maximise performance through an integrated claims management system. Our claims management system helps insurers and reinsurers maximise performance through business process automation, enabling teams to save time and get ahead. This is the important part, however. We focus on empowering people through automation so that claims teams can concentrate on challenges that only humans can handle.
There is no doubt that developing AI and ML capabilities to analyse social, historical, and behavioural data will help insurance companies to gain a more granular understanding of their customers and help to develop better solutions. But more precise risk prediction, data insights, and automated settlements, will not replace the human touch anytime soon. These kinds of technologies will augment claims handlers’ ability to provide a better service, certainly in areas of the specialty insurance classes, which deal in billion dollar plus claims.
But as the Financial Times reports, the rise of AI-powered insurance worries researchers that this new way of doing things creates unfairness and could even undermine the risk-pooling model that is key to the industry, making it impossible for some people to find cover. “Yes, you won’t pay for the claims of your accident-prone neighbour, but then again, no one else will then pay for your claims — just you,” said Duncan Minty, an independent consultant on ethics in the sector. There is a danger, he added, of “social sorting”, where groups of people perceived as riskier cannot buy insurance.
As DOCOsoft has written in a previous blog on the ethics of AI, these areas are relevant to insurance and need to be thought through carefully because not all of the benefits associated with AI are necessarily positive. Of course, the potential opportunities are great, but the negatives could include AI bias, loss of certain jobs, a shift in human experience as machines take on more responsibilities, global regulations wars as different regimes adopt different approaches to ensure consent and transparency, accelerated hacking and AI terrorism.
The fact is, however, that AI promises enormous potential rewards to businesses that can harness and control the technology in an ethical and smart way, as we will discuss in our next blog.