Detection of interacting variables for generalized linear models via neural networks

DOI10.1007/S13385-023-00362-4MaRDI QIDQ6593147zbMATHFDO

Authors Yevhen Havrylenko, Julia Heger

Publication date 26 August 2024

Published in European Actuarial Journal (Search for Journal in Brave)

zbMATH Keywords

generalized linear modelneural networkinteraction detectionmodel interpretabilityinsurance claims prediction

Mathematics Subject Classification ID

Actuarial mathematics (91G05) Artificial neural networks and deep learning (68T07)

Recommendations

• Machine learning with high-cardinality categorical features in actuarial applications
• Boosting insights in insurance tariff plans with tree-based machine learning methods
• Enhancing actuarial non-life pricing models via transformers
• Enhanced gradient boosting for zero-inflated insurance claims and comparative analysis of CatBoost , XGBoost , and LightGBM
• Telematics combined actuarial neural networks for cross-sectional and longitudinal claim count data

Cites work

• scientific article; zbMATH DE number 6378127 (Why is no real title available?)
• scientific article; zbMATH DE number 845714 (Why is no real title available?)
• A data driven binning strategy for the construction of insurance tariff classes
• Actuarial Modelling of Claim Counts
• Bias regularization in neural network models for general insurance pricing
• LocalGLMnet: interpretable deep learning for tabular data
• Non-life insurance pricing with generalized linear models
• Predictive learning via rule ensembles
• Statistical foundations of actuarial learning and its applications

This page was built for publication: Detection of interacting variables for generalized linear models via neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6593147)