Comparing Predictive Models for Dependent Risk Pricing
Variance · 17.11.2025 · 18
DOI: 10.66573/001c.146234 ↗Kurz gefasst
Fachartikel in der Zeitschrift Variance, online erschienen am 17.11.2025. Verfasst von Giorgio Alfredo Spedicato und 1 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben.
Abstract (Originalsprache)
This paper explores the application of advanced machine learning (ML) techniques, particularly gradient-boosted trees (GBTs), multilayer perceptron deep learning (MLP DL), and transformer-based deep learning (TRF DL), for the pricing of multiperil insurance policies—aiming to address the potential dependencies among different covers and between frequency and severity of claims. The predictive performance of these techniques is compared on three distinct actuarial datasets. While all methods provide reasonable predictive performance, the TRF consistently outperforms the others, demonstrating superior ability to capture interdependencies among perils and risk components, although it is computationally more complex. The paper also investigates model interpretation and variable importance, emphasizing practical considerations for actuarial applications. This paper was supported by a 2023 individual grant from the CAS and the Society of Actuaries. Address for Correspondence: spedicato_giorgio@yahoo.it
Zitieren
APA
Spedicato, G. A., & Richman, R. (2025). Comparing Predictive Models for Dependent Risk Pricing. Variance, 18. https://doi.org/10.66573/001c.146234
Vancouver
Spedicato GA, Richman R. Comparing Predictive Models for Dependent Risk Pricing. Variance. 2025;18. doi:10.66573/001c.146234
BibTeX
@article{Spedicato2025,
author = {Spedicato, Giorgio Alfredo and Richman, Ronald},
title = {Comparing Predictive Models for Dependent Risk Pricing},
journal = {Variance},
year = {2025},
volume = {18},
doi = {10.66573/001c.146234}
}
EUVIMED