Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/313671 
Year of Publication: 
2023
Citation: 
[Journal:] European Actuarial Journal [ISSN:] 2190-9741 [Volume:] 14 [Issue:] 2 [Publisher:] Springer [Place:] Berlin, Heidelberg [Year:] 2023 [Pages:] 551-580
Publisher: 
Springer, Berlin, Heidelberg
Abstract: 
The quality of generalized linear models (GLMs), frequently used by insurance companies, depends on the choice of interacting variables. The search for interactions is time-consuming, especially for data sets with a large number of variables, depends much on expert judgement of actuaries, and often relies on visual performance indicators. Therefore, we present an approach to automating the process of finding interactions that should be added to GLMs to improve their predictive power. Our approach relies on neural networks and a model-specific interaction detection method, which is computationally faster than the traditionally used methods like Friedman’s H-Statistic or SHAP values. In numerical studies, we provide the results of our approach on artificially generated data as well as open-source data.
Subjects: 
Neural network
Model interpretability
Generalized linear model
Interaction detection
Insurance claims prediction
Persistent Identifier of the first edition: 
Creative Commons License: 
cc-by Logo
Document Type: 
Article
Document Version: 
Published Version

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.