Key result
Neural network models improved health insurance pricing accuracy compared to classical regression models, achieving a lower average out-of-sample deviance (8.54 vs 8.61).
Why the study?
Most actuarial machine learning research focuses on property and casualty insurance, while applying such techniques in health insurance pricing remains largely unexplored.
Absolute Event Rate: 8.54% vs 8.61%
Neural network models outperform classical regression models in pricing health insurance coverage by improving accuracy and risk diversification.
Neural networks may refine insurance pricing; leaves open validation in cardiovascular risk models.
In recent years, the actuarial literature involving machine learning in insurance pricing has flourished. However, most actuarial machine learning research focuses on property and casualty insurance, while using such techniques in health insurance is yet to be explored. In this paper, we discuss the use of neural networks to set the price of health insurance coverage following the structure of a classical frequency-severity model. In particular, we propose negative multinomial neural networks to jointly model the frequency of possibly correlated medical claims and Gamma neural networks to estimate the expected claim severity. Using a case study based on real-world health insurance data, we highlight the overall better performance of the neural network models with respect to more established regression models, both in terms of accuracy (frequency models achieve an average out-of-sample deviance of 8.54 compared to 8.61 for classical regressions) and risk diversification, as indicated by the ABC lift metric, which is 5.62×10−3 for neural networks versus 8.27×10−3 for traditional models.
No takes yet. Share an insight, caveat, or question.
Laporta et al. (2025) studied Health insurance pricing. Neural network models vs. Classical regression models was evaluated on Average out-of-sample deviance. Neural network models improved health insurance pricing accuracy compared to classical regression models, achieving a lower average out-of-sample deviance (8.54 vs 8.61).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: