Enhanced gradient boosting for zero-inflated insurance claims and comparative analysis of CatBoost, XGBoost, and LightGBM

Banghee So

Scandinavian Actuarial Journal, 2024, vol. 2024, issue 10, 1013-1035

Abstract: The property and casualty (P&C) insurance industry faces challenges in developing claim predictive models due to the highly right-skewed distribution of positive claims with excess zeros. To address this, actuarial science researchers have employed ‘zero-inflated’ models that combine a traditional count model and a binary model. This paper investigates the use of boosting algorithms to process insurance claim data, including zero-inflated telematics data, to construct claim frequency models. Three popular gradient boosting libraries - XGBoost, LightGBM, and CatBoost -- are evaluated and compared to determine the most suitable library for training insurance claim data and fitting actuarial frequency models. Through a comprehensive analysis of two distinct datasets, it is determined that CatBoost is the best for developing auto claim frequency models based on predictive performance. Furthermore, we propose a new zero-inflated Poisson boosted tree model, with variation in the assumption about the relationship between inflation probability p and distribution mean μ, and find that it outperforms others depending on the characteristics of the data. This model enables us to take advantage of particular CatBoost tools, which makes it easier and more convenient to investigate the effects and interactions of various risk features on the frequency model when using telematics data.

Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/03461238.2024.2365390 (text/html)
Access to full text is restricted to subscribers.

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:taf:sactxx:v:2024:y:2024:i:10:p:1013-1035

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/sact20

DOI: 10.1080/03461238.2024.2365390

Access Statistics for this article

Scandinavian Actuarial Journal is currently edited by Boualem Djehiche

More articles in Scandinavian Actuarial Journal from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().