{"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}
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.
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.