قالب وردپرس درنا توس
Home / Insurance / Machine learning is making an impact in insurance, but the challenges remain

Machine learning is making an impact in insurance, but the challenges remain



SAN ANTONIO – New tools such as artificial intelligence and natural language processing are used in the insurance sector, but costs are still high and there are issues of bias introduced in machine learning, according to a speaker at the Public Risk Management Association’s annual meeting on Monday.

“Everything is smart these days,” said Brian Billings, vice president of predictive analytics at Ballwin, Missouri, for Midwest Employers Casualty Co., part of WR Berkeley Corp., and devices such as cell phones and televisions are now collecting data from their users. “All that technology is driven by the use of data.”

Machine learning, including artificial intelligence and natural language processing, takes data collected and tries to predict some kind of outcome, said Mr. Billings, such as a numerical value or, in the case of the insurance sector, a claims scenario.

With natural language processing, a model is trained to read text, said Mr. Billings. Such technology can take a 40-page printout summary and extract specific relevant text, such as the names of all physicians or attorneys, or medical notes. “It has enormous implications in the claim adjustment space.”

; He noted that his company has such tools in use.

Although the technology remains expensive, Mr. Billings is convinced that the tools will reach a “democratization point” in their use penetration and eventually become more affordable. “I think the day will come where it will be available and not be prohibitively expensive to have on hand,” he said.

The introduction of bias in the training of machines and models is still a problem.

“Bias is a problem, definitely,” said Mr. Billings and added that it is “absolutely” something to watch out for. However, he is convinced that the technology will continue to develop and be used more widely in the insurance sector.

“Technology will not slow down,” he said. “The amount of data we have and generate will not decrease. We will see more and more of this.”


Source link