Machine Learning in Property and Casualty Insurance: A Review for Pricing and Reserving

Abstract

In the past 25 years, computer scientists and statisticians developed machine learning algorithms capable of modeling highly non-linear transformations and interactions of input features. While actuaries use GLMs frequently in practice, only in the past few years have they begun studying these newer algorithms to tackle insurance-related tasks. This work aims to review the applications of machine learning to the actuarial science field and present the current state-of-the-art in ratemaking and reserving. It first gives an overview of machine learning algorithms, then briefly outlines their applications in actuarial science tasks. Finally, the paper summarizes the future trends of machine learning for the insurance industry.