Machine Learning with High-Cardinality Categorical Features in Actuarial Applications

Benjamin Avanzi, Greg Taylor, Melantha Wang, Bernard Wong
{"title":"Machine Learning with High-Cardinality Categorical Features in Actuarial Applications","authors":"Benjamin Avanzi, Greg Taylor, Melantha Wang, Bernard Wong","doi":"10.1017/asb.2024.7","DOIUrl":null,"url":null,"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 <jats:italic>Generalised Linear Mixed Model Neural Network</jats:italic> (“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 exponential dispersion (ED) family makes it widely applicable to many actuarial contexts and beyond. In order to facilitate the application of GLMMNet to large datasets, we use variational inference to estimate its parameters—both traditional mean field and versions utilising textual information underlying the high-cardinality categorical features.We illustrate and compare the GLMMNet against existing approaches in a range of simulation experiments as well as in a real-life insurance case study. A notable feature for both our simulation experiment and the real-life case study is a comparatively low signal-to-noise ratio, which is a feature common in actuarial applications. We find that the GLMMNet often outperforms or at least performs comparably with an entity-embedded neural network in these settings, while providing the additional benefit of transparency, which is particularly valuable in practical applications.Importantly, while our model was motivated by actuarial applications, it can have wider applicability. The GLMMNet would suit any applications that involve high-cardinality categorical variables and where the response cannot be sufficiently modelled by a Gaussian distribution, especially where the inherent noisiness of the data is relatively high.","PeriodicalId":501189,"journal":{"name":"ASTIN Bulletin: The Journal of the IAA","volume":"10 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ASTIN Bulletin: The Journal of the IAA","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1017/asb.2024.7","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

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 exponential dispersion (ED) family makes it widely applicable to many actuarial contexts and beyond. In order to facilitate the application of GLMMNet to large datasets, we use variational inference to estimate its parameters—both traditional mean field and versions utilising textual information underlying the high-cardinality categorical features.We illustrate and compare the GLMMNet against existing approaches in a range of simulation experiments as well as in a real-life insurance case study. A notable feature for both our simulation experiment and the real-life case study is a comparatively low signal-to-noise ratio, which is a feature common in actuarial applications. We find that the GLMMNet often outperforms or at least performs comparably with an entity-embedded neural network in these settings, while providing the additional benefit of transparency, which is particularly valuable in practical applications.Importantly, while our model was motivated by actuarial applications, it can have wider applicability. The GLMMNet would suit any applications that involve high-cardinality categorical variables and where the response cannot be sufficiently modelled by a Gaussian distribution, especially where the inherent noisiness of the data is relatively high.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
精算应用中的高心率分类特征机器学习
高心率分类特征普遍存在于精算数据中(如商业财产保险中的职业)。在这项工作中,我们提出了一种新颖的广义线性混合模型神经网络("GLMMNet")方法,用于对高心率分类特征建模。GLMMNet 在深度学习框架中集成了广义线性混合模型,提供了神经网络的预测能力和随机效应估计的透明度,后者无法从实体嵌入模型中获得。此外,它还能灵活地处理指数离散(ED)族中的任何分布,因此可广泛应用于许多精算领域及其他领域。为了便于将 GLMMNet 应用于大型数据集,我们使用变异推理来估算其参数--既包括传统的均值域,也包括利用高心率分类特征的文本信息的版本。模拟实验和实际案例研究的一个显著特点是信噪比相对较低,这在精算应用中很常见。我们发现,在这些情况下,GLMMNet 的性能往往优于实体嵌入式神经网络,或至少与之相当,同时还具有透明度高的额外优势,这在实际应用中尤为重要。GLMMNet 适用于任何涉及高心率分类变量的应用,以及无法用高斯分布对响应进行充分建模的应用,尤其是数据固有噪声相对较高的应用。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Impact of correlation between interest rates and mortality rates on the valuation of various life insurance products Generic framework for a coherent integration of experience and exposure rating in reinsurance Strategic underreporting and optimal deductible insurance Multidimensional credibility: A new approach based on joint distribution function Machine Learning with High-Cardinality Categorical Features in Actuarial Applications
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1