Tariff Analysis in Automobile Insurance: Is It Time to Switch from Generalized Linear Models to Generalized Additive Models?

Zuleyka Díaz Martínez, José Fernández Menéndez and Luis Javier García Villalba ()
Additional contact information
Zuleyka Díaz Martínez: Group of Analysis, Security and Systems (GASS), Department of Financial and Actuarial Economics & Statistics, Faculty of Economics and Business Administration, Universidad Complutense de Madrid (UCM), Campus Somosaguas, 28223 Madrid, Spain
José Fernández Menéndez: Department of Business Administration, Faculty of Economics and Business Administration, Universidad Complutense de Madrid (UCM), Campus Somosaguas, 28223 Madrid, Spain
Luis Javier García Villalba: Group of Analysis, Security and Systems (GASS), Department of Software Engineering and Artificial Intelligence (DISIA), Faculty of Computer Science and Engineering, Office 431, Universidad Complutense de Madrid (UCM), Calle Profesor José García Santesmases, 9, Ciudad Universitaria, 28040 Madrid, Spain

Mathematics, 2023, vol. 11, issue 18, 1-16

Abstract: Generalized Linear Models (GLMs) are the standard tool used for pricing in the field of automobile insurance. Generalized Additive Models (GAMs) are more complex and computationally intensive but allow taking into account nonlinear effects without the need to discretize the explanatory variables. In addition, they fit perfectly into the mental framework shared by actuaries and are easier to use and interpret than machine learning models, such as trees or neural networks. This work compares both the GLM and GAM approaches, using a wide sample of policies to assess their differences in terms of quality of predictions, complexity of use, and time of execution. The results show that GAMs are a powerful alternative to GLMs, particularly when “big data” implementations of GAMs are used.

Keywords: automobile insurance; generalized additive models; splines; tariff analysis (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/18/3906/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/18/3906/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:18:p:3906-:d:1239584

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().