Journal article
Machine Learning with High-Cardinality Categorical Features in Actuarial Applications
Benjamin Avanzi, Greg Taylor, Melantha Wang, Bernard Wong
Astin Bulletin: The Journal of the IAA | Cambridge University Press | Published : 2024
DOI: 10.1017/asb.2024.7
Abstract
High-cardinality categorical features are pervasive in actuarial data (e.g., occupation in commercial property insurance). Standard categorical encoding methods like one-hot encoding are inadequate in these settings. In this work, we present a novel Generalised Linear Mixed Model Neural Network (GLMMNet) approach to the modelling of high-cardinality categorical features. The GLMMNet integrates a generalised linear mixed model in a deep learning framework, offering the predictive power of neural networks and the transparency of random effects estimates, the latter of which cannot be obtained from the entity embedding models. Further, its flexibility to deal with any distribution in the expone..
View full abstractRelated Projects (1)
Grants
Awarded by Australian Research Council's Discovery Project
Funding Acknowledgements
This work was presented at the Australasian Actuarial Education and Research Symposium (AAERS) in November 2022 (Canberra, Australia), the International Congress of Actuaries in May 2023 (Sydney, Australia), and the Insurance Data Science Conference in June 2023 (London, UK). The authors are grateful for the constructive comments received from colleagues present at the event.The authors are also grateful to Jovana Kolar, for her assistance in coding and running the experiments, and to Mario Wuethrichand three anonymous reviewers, for their insightful comments that led to significant improvements of the paper.This research was supported under Australian Research Council's Discovery Project DP200101859 funding scheme. MelanthaWang acknowledges financial support from UNSW Australia Business School. The views expressed herein are those of the authorsand are not necessarily those of the supporting organisations.