Detection of interacting variables for generalized linear models via neural networks

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Detection of interacting variables for generalized linear models via neural networks. / Havrylenko, Yevhen; Heger, Julia.

I: European Actuarial Journal, 2024.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Havrylenko, Y & Heger, J 2024, 'Detection of interacting variables for generalized linear models via neural networks', European Actuarial Journal. https://doi.org/10.1007/s13385-023-00362-4

APA

Havrylenko, Y., & Heger, J. (2024). Detection of interacting variables for generalized linear models via neural networks. European Actuarial Journal. https://doi.org/10.1007/s13385-023-00362-4

Vancouver

Havrylenko Y, Heger J. Detection of interacting variables for generalized linear models via neural networks. European Actuarial Journal. 2024. https://doi.org/10.1007/s13385-023-00362-4

Author

Havrylenko, Yevhen ; Heger, Julia. / Detection of interacting variables for generalized linear models via neural networks. I: European Actuarial Journal. 2024.

Bibtex

@article{77fe7624868c47b9992323afe40c96b3,
title = "Detection of interacting variables for generalized linear models via neural networks",
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{\textquoteright}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.",
keywords = "Generalized linear model, Insurance claims prediction, Interaction detection, Model interpretability, Neural network",
author = "Yevhen Havrylenko and Julia Heger",
note = "Publisher Copyright: {\textcopyright} 2023, The Author(s).",
year = "2024",
doi = "10.1007/s13385-023-00362-4",
language = "English",
journal = "European Actuarial Journal",
issn = "2190-9733",
publisher = "Springer",

}

RIS

TY - JOUR

T1 - Detection of interacting variables for generalized linear models via neural networks

AU - Havrylenko, Yevhen

AU - Heger, Julia

N1 - Publisher Copyright: © 2023, The Author(s).

PY - 2024

Y1 - 2024

N2 - 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.

AB - 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.

KW - Generalized linear model

KW - Insurance claims prediction

KW - Interaction detection

KW - Model interpretability

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=85175378985&partnerID=8YFLogxK

U2 - 10.1007/s13385-023-00362-4

DO - 10.1007/s13385-023-00362-4

M3 - Journal article

AN - SCOPUS:85175378985

JO - European Actuarial Journal

JF - European Actuarial Journal

SN - 2190-9733

ER -

ID: 372718973