Towards Explainability of Machine Learning Models in Insurance Pricing

Kevin Kuo; Daniel Lupton

Towards Explainability of Machine Learning Models in Insurance Pricing

Risk Management 2020-03-25 v1 Machine Learning

Authors: Kevin Kuo , Daniel Lupton

Abstract

Machine learning methods have garnered increasing interest among actuaries in recent years. However, their adoption by practitioners has been limited, partly due to the lack of transparency of these methods, as compared to generalized linear models. In this paper, we discuss the need for model interpretability in property & casualty insurance ratemaking, propose a framework for explaining models, and present a case study to illustrate the framework.

Keywords

financial technology and innovation insurance and risk management asset pricing and market equilibrium

Cite

@article{arxiv.2003.10674,
  title  = {Towards Explainability of Machine Learning Models in Insurance Pricing},
  author = {Kevin Kuo and Daniel Lupton},
  journal= {arXiv preprint arXiv:2003.10674},
  year   = {2020}
}

Related papers

View all related →

Machine Learning · Statistics

Model Transparency and Interpretability : Survey and Application to the Insurance Industry

Dimitri Delcaillau, Antoine Ly, Alize Papp, Franck Vermet

2022-09-02

Materials Science · Physics

Interpretability of machine-learning models in physical sciences