Predictive modelling in insurance is performed for many years by actuaries with the help of statistical models (e.g. Generalized Linear Models - GLM).

Machine learning (ML) techniques are now more and more popular in the insurance industry and have a lot of applications (pricing, reserving, claims management, underwriting).

In this webinar, we focus on the application of machine learning techniques to non-life pricing and underwriting.

After presenting some useful machine learning techniques for actuaries (focusing on tree-based models: Gradient Boosting Machine, Random Forest and Explainable Boosting Machine), we analyze their potential applications for pricing as well as for other underwriting activities (profitability analysis, competition analysis, portfolio management). We also discuss the concepts of direct and indirect discrimination and fairness in pricing.