Historically, insurance underwriters have relied on information provided on applications to assess the risks surrounding a potential client. The trouble, of course, is that applicants could be dishonest or make mistakes, rendering these risk assessments inaccurate.
Machine learning, specifically natural language understanding (NLU), enables insurers to pore through more abstract sources of information, such as Yelp reviews, social media postings, SEC filings and so on, and pull pertinent information together to more adequately assess the insurance carrier’s potential exposure.