Loading [Contrib]/a11y/accessibility-menu.js
Kuo, Kevin, and Daniel Lupton. 2023. “Towards Explainability of Machine Learning Models in Insurance Pricing.” Variance 16 (1).
Download all (5)
  • Figure 1. A simple decision tree for loss cost prediction.
  • Figure 2. A more complex decision tree.
  • Figure 3. Permutation feature importances for the neural network model.
  • Figure 4. Partial dependence plot for the neural network model.
  • Figure 5. Variable contribution plot for the neural network model.


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.

Accepted: June 16, 2020 EDT