IMPROVING INSURANCE TARIFFS BASED ON ACTUARIAL AND MACHINE LEARNING MODELS FOR INSURANCE RISK ASSESSMENT
Keywords:
insurance tariff; actuarial modeling; generalized linear models; machine learning; gradient boosting; risk assessment; explainable artificial intelligence.Abstract
This thesis proposes a hybrid framework that improves insurance tariffs by combining actuarial and machine learning models. Generalized linear models form an interpretable frequency-severity tariff, while gradient boosting captures nonlinear effects and risk-factor interactions omitted from the baseline. The framework adds out-of-sample validation, explainability analysis, portfolio-level calibration and regulatory review. It supports more risk-adequate and transparent pricing, particularly in developing insurance markets such as Uzbekistan.References
1. Ohlsson, E., & Johansson, B. (2010). Non-Life Insurance Pricing with Generalized Linear Models. Springer.
2. Henckaerts, R., Côté, M.-P., Antonio, K., & Verbelen, R. (2021). Boosting insights in insurance tariff plans with tree-based machine learning methods. North American Actuarial Journal, 25(2), 255–285.
3. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794.
4. Schelldorfer, J., & Wüthrich, M. V. (2019). Nesting classical actuarial models into neural networks. Available at SSRN.
5. Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774.
6. Lindholm, M., Richman, R., Tsanakas, A., & Wüthrich, M. V. (2022). Discrimination-free insurance pricing. ASTIN Bulletin, 52(1), 55–89.
7. Wüthrich, M. V., & Merz, M. (2023). Statistical Foundations of Actuarial Learning and its Applications. Springer.

