寻找僵尸的机器学习:预测公司账目的困境和价值缺失

IF 2.8 4区 管理学 Q2 BUSINESS
Falco J Bargagli-Stoffi, Fabio Incerti, Massimo Riccaboni, Armando Rungi
{"title":"寻找僵尸的机器学习:预测公司账目的困境和价值缺失","authors":"Falco J Bargagli-Stoffi, Fabio Incerti, Massimo Riccaboni, Armando Rungi","doi":"10.1093/icc/dtad049","DOIUrl":null,"url":null,"abstract":"Abstract In this contribution, we propose machine learning techniques to predict zombie firms. First, we derive the risk of failure by training and testing our algorithms on disclosed financial information and nonrandom missing values of 304,906 firms active in Italy from 2008 to 2017. We then identify the highest financial distress conditional on predictions that lie above a threshold for which a combination of the false positive rate (false prediction of firm failure) and the false negative rate (false prediction of active firms) is minimized. Therefore, we identify zombies as firms that remain in financial distress, i.e., whose forecasts fall into the risk category above the threshold for at least three consecutive years. To this end, we implement a gradient boosting algorithm (XGBoost) that exploits information about missing values. The inclusion of missing values in our prediction model is crucial because patterns of undisclosed accounts are correlated with firm failure. Finally, we show that our preferred machine learning algorithm outperforms (i) proxy models such as Z-scores and the distance-to-default, (ii) traditional econometric methods, and (iii) other widely used machine learning techniques. We provide evidence that zombies are less productive and smaller on average and that they tend to increase in times of crisis. Finally, we argue that our application can help financial institutions and public authorities design evidence-based policies—e.g., optimal bankruptcy laws and information disclosure policies.","PeriodicalId":48243,"journal":{"name":"Industrial and Corporate Change","volume":"3 1","pages":"0"},"PeriodicalIF":2.8000,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine learning for zombie hunting: predicting distress from firms’ accounts and missing values\",\"authors\":\"Falco J Bargagli-Stoffi, Fabio Incerti, Massimo Riccaboni, Armando Rungi\",\"doi\":\"10.1093/icc/dtad049\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract In this contribution, we propose machine learning techniques to predict zombie firms. First, we derive the risk of failure by training and testing our algorithms on disclosed financial information and nonrandom missing values of 304,906 firms active in Italy from 2008 to 2017. We then identify the highest financial distress conditional on predictions that lie above a threshold for which a combination of the false positive rate (false prediction of firm failure) and the false negative rate (false prediction of active firms) is minimized. Therefore, we identify zombies as firms that remain in financial distress, i.e., whose forecasts fall into the risk category above the threshold for at least three consecutive years. To this end, we implement a gradient boosting algorithm (XGBoost) that exploits information about missing values. The inclusion of missing values in our prediction model is crucial because patterns of undisclosed accounts are correlated with firm failure. Finally, we show that our preferred machine learning algorithm outperforms (i) proxy models such as Z-scores and the distance-to-default, (ii) traditional econometric methods, and (iii) other widely used machine learning techniques. We provide evidence that zombies are less productive and smaller on average and that they tend to increase in times of crisis. Finally, we argue that our application can help financial institutions and public authorities design evidence-based policies—e.g., optimal bankruptcy laws and information disclosure policies.\",\"PeriodicalId\":48243,\"journal\":{\"name\":\"Industrial and Corporate Change\",\"volume\":\"3 1\",\"pages\":\"0\"},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2023-10-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Industrial and Corporate Change\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1093/icc/dtad049\",\"RegionNum\":4,\"RegionCategory\":\"管理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"BUSINESS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Industrial and Corporate Change","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/icc/dtad049","RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"BUSINESS","Score":null,"Total":0}
引用次数: 0

摘要

在这篇文章中,我们提出了机器学习技术来预测僵尸企业。首先,我们对2008年至2017年在意大利活跃的304,906家公司的披露财务信息和非随机缺失值进行了训练和测试,得出了失败的风险。然后,我们确定了最高的财务困境,条件是预测高于一个阈值,在这个阈值下,假阳性率(对企业倒闭的错误预测)和假阴性率(对活跃企业的错误预测)的组合最小。因此,我们将僵尸公司定义为仍然处于财务困境的公司,即其预测至少连续三年落入高于阈值的风险类别。为此,我们实现了一个梯度增强算法(XGBoost),它利用了关于缺失值的信息。在我们的预测模型中包含缺失值是至关重要的,因为未披露账户的模式与公司失败相关。最后,我们表明,我们首选的机器学习算法优于(i)代理模型,如z分数和默认距离,(ii)传统的计量经济学方法,以及(iii)其他广泛使用的机器学习技术。我们提供的证据表明,僵尸的生产力较低,平均体型较小,而且在危机时期往往会增加。最后,我们认为我们的应用程序可以帮助金融机构和公共当局设计基于证据的政策。最优破产法律和信息披露政策。
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 for zombie hunting: predicting distress from firms’ accounts and missing values
Abstract In this contribution, we propose machine learning techniques to predict zombie firms. First, we derive the risk of failure by training and testing our algorithms on disclosed financial information and nonrandom missing values of 304,906 firms active in Italy from 2008 to 2017. We then identify the highest financial distress conditional on predictions that lie above a threshold for which a combination of the false positive rate (false prediction of firm failure) and the false negative rate (false prediction of active firms) is minimized. Therefore, we identify zombies as firms that remain in financial distress, i.e., whose forecasts fall into the risk category above the threshold for at least three consecutive years. To this end, we implement a gradient boosting algorithm (XGBoost) that exploits information about missing values. The inclusion of missing values in our prediction model is crucial because patterns of undisclosed accounts are correlated with firm failure. Finally, we show that our preferred machine learning algorithm outperforms (i) proxy models such as Z-scores and the distance-to-default, (ii) traditional econometric methods, and (iii) other widely used machine learning techniques. We provide evidence that zombies are less productive and smaller on average and that they tend to increase in times of crisis. Finally, we argue that our application can help financial institutions and public authorities design evidence-based policies—e.g., optimal bankruptcy laws and information disclosure policies.
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
5.10
自引率
4.00%
发文量
51
期刊介绍: The journal covers the following: the internal structures of firms; the history of technologies; the evolution of industries; the nature of competition; the decision rules and strategies; the relationship between firms" characteristics and the institutional environment; the sociology of management and of the workforce; the performance of industries over time; the labour process and the organization of production; the relationship between, and boundaries of, organizations and markets; the nature of the learning process underlying technological and organizational change.
×
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