Year: 2025
Type: article
Abstract: In recent years, the actuarial literature involving machine learning in insurance pricing has flourished.However, most actuarial machine learning research focuses on property and casualtyinsurance, while the use of 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 thestructure of a classical frequency-severity model. In particular, we propose negative multinomialneural networks to jointly model the frequency of possibly correlated medical claims, and Gammaneural networks to estimate the expected claim severity.Through a case study based on a health insurance dataset, we highlight the overall better performanceof the neural network models with respect to more established regression models, both interms of accuracy and risk diversification.
Source: Risks
Institution: Sapienza University of Rome
Language: English
Topic: Probability and Risk Models
Field: Decision Sciences
Domain: Social Sciences
Open Access status: gold
Estimated APC paid: $2,172
OpenAlex ID: W4409734228