Proxy Modeling in Life Insurance Companies With the Use of Machine Learning Algorithms

Abstract

In this paper, we present how ideas from artificial intelligence field can be utilized in proxy modeling problem that is faced by actuarial departments of life insurance companies. The current approaches are reviewed, exposing their incapability to fully mimic the complexity and non-linearity of cash-flow projection models. In order to increase the quality of proxy models, we propose to apply selected machine learning algorithms as well as provide an overview of the theory behind them and present the numerical results with a comparison of model errors for different estimators. The study is performed on real data generated by a large reinsurance company. The text can serve as a guideline for companies willing to introduce machine learning algorithms in their proxy modeling processes.