机器学习和盈利能力变化的预测

IF 3.2 3区 管理学 Q1 BUSINESS, FINANCE
Stewart Jones, William J. Moser, Matthew M. Wieland
{"title":"机器学习和盈利能力变化的预测","authors":"Stewart Jones,&nbsp;William J. Moser,&nbsp;Matthew M. Wieland","doi":"10.1111/1911-3846.12888","DOIUrl":null,"url":null,"abstract":"<p>This study uses machine-learning methods to predict next-period change in profitability based on a model proposed by Penman and Zhang (2004, Working paper, Columbia University and University of California, Berkeley; “PZ”). We find that new machine-learning methods predict out of sample substantially better than traditional regression methods and provide richer interpretations about the role and impact of different predictor variables through their nonlinear relationships and interaction effects. For example, our results contrast with previous research by showing that both components of the DuPont decomposition (change in profit margin and change in asset turnover) are informative of next-period changes in profitability. Our results are robust across different performance metrics, alternative machine-learning models, and software. Furthermore, an unconstrained machine-learning model using a larger feature space could not significantly improve the performance of the PZ model. PZ variables alone accounted for most of the explanatory power of the unconstrained model, suggesting the PZ model is both well specified (in terms of feature selection) and robust in higher dimensional settings. With respect to the economic significance of this information, we find mixed results. The market appears to adjust its expectations more in line with the machine-learning predictions relative to the PZ model but the portfolio returns are not significantly different.</p>","PeriodicalId":10595,"journal":{"name":"Contemporary Accounting Research","volume":"40 4","pages":"2643-2672"},"PeriodicalIF":3.2000,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/1911-3846.12888","citationCount":"0","resultStr":"{\"title\":\"Machine learning and the prediction of changes in profitability\",\"authors\":\"Stewart Jones,&nbsp;William J. Moser,&nbsp;Matthew M. Wieland\",\"doi\":\"10.1111/1911-3846.12888\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>This study uses machine-learning methods to predict next-period change in profitability based on a model proposed by Penman and Zhang (2004, Working paper, Columbia University and University of California, Berkeley; “PZ”). We find that new machine-learning methods predict out of sample substantially better than traditional regression methods and provide richer interpretations about the role and impact of different predictor variables through their nonlinear relationships and interaction effects. For example, our results contrast with previous research by showing that both components of the DuPont decomposition (change in profit margin and change in asset turnover) are informative of next-period changes in profitability. Our results are robust across different performance metrics, alternative machine-learning models, and software. Furthermore, an unconstrained machine-learning model using a larger feature space could not significantly improve the performance of the PZ model. PZ variables alone accounted for most of the explanatory power of the unconstrained model, suggesting the PZ model is both well specified (in terms of feature selection) and robust in higher dimensional settings. With respect to the economic significance of this information, we find mixed results. The market appears to adjust its expectations more in line with the machine-learning predictions relative to the PZ model but the portfolio returns are not significantly different.</p>\",\"PeriodicalId\":10595,\"journal\":{\"name\":\"Contemporary Accounting Research\",\"volume\":\"40 4\",\"pages\":\"2643-2672\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2023-07-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1111/1911-3846.12888\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Contemporary Accounting Research\",\"FirstCategoryId\":\"91\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1111/1911-3846.12888\",\"RegionNum\":3,\"RegionCategory\":\"管理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"BUSINESS, FINANCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Contemporary Accounting Research","FirstCategoryId":"91","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/1911-3846.12888","RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BUSINESS, FINANCE","Score":null,"Total":0}
引用次数: 0

摘要

本研究基于Penman和Zhang(2004,工作论文,哥伦比亚大学和加州大学伯克利分校)提出的模型,使用机器学习方法预测下一时期盈利能力的变化;“PZ”)。我们发现,新的机器学习方法比传统的回归方法更好地预测样本外,并通过非线性关系和相互作用对不同预测变量的作用和影响提供更丰富的解释。例如,我们的结果与之前的研究形成对比,表明杜邦分解的两个组成部分(利润率变化和资产周转率变化)都能提供下一时期盈利能力变化的信息。我们的结果在不同的性能指标、替代机器学习模型和软件中都是稳健的。此外,使用更大特征空间的无约束机器学习模型不能显著提高PZ模型的性能。PZ变量单独占了无约束模型的大部分解释力,这表明PZ模型既指定得很好(就特征选择而言),又在高维设置中具有鲁棒性。关于这一信息的经济意义,我们发现结果好坏参半。相对于PZ模型,市场似乎更能根据机器学习预测来调整预期,但投资组合回报并没有显著差异。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Machine learning and the prediction of changes in profitability

Machine learning and the prediction of changes in profitability

This study uses machine-learning methods to predict next-period change in profitability based on a model proposed by Penman and Zhang (2004, Working paper, Columbia University and University of California, Berkeley; “PZ”). We find that new machine-learning methods predict out of sample substantially better than traditional regression methods and provide richer interpretations about the role and impact of different predictor variables through their nonlinear relationships and interaction effects. For example, our results contrast with previous research by showing that both components of the DuPont decomposition (change in profit margin and change in asset turnover) are informative of next-period changes in profitability. Our results are robust across different performance metrics, alternative machine-learning models, and software. Furthermore, an unconstrained machine-learning model using a larger feature space could not significantly improve the performance of the PZ model. PZ variables alone accounted for most of the explanatory power of the unconstrained model, suggesting the PZ model is both well specified (in terms of feature selection) and robust in higher dimensional settings. With respect to the economic significance of this information, we find mixed results. The market appears to adjust its expectations more in line with the machine-learning predictions relative to the PZ model but the portfolio returns are not significantly different.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
6.20
自引率
11.10%
发文量
97
期刊介绍: Contemporary Accounting Research (CAR) is the premiere research journal of the Canadian Academic Accounting Association, which publishes leading- edge research that contributes to our understanding of all aspects of accounting"s role within organizations, markets or society. Canadian based, increasingly global in scope, CAR seeks to reflect the geographical and intellectual diversity in accounting research. To accomplish this, CAR will continue to publish in its traditional areas of excellence, while seeking to more fully represent other research streams in its pages, so as to continue and expand its tradition of excellence.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信