主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院

中国管理科学 ›› 2023, Vol. 31 ›› Issue (2): 18-29.doi: 10.16381/j.cnki.issn1003-207x.2020.2263

• 论文 • 上一篇    下一篇

基于信息披露文本的上市公司信用风险预警——来自中文年报管理层讨论与分析的经验证据

李成刚1, 2, 贾鸿业3, 赵光辉4, 付红5   

  1. 1.贵州财经大学大数据应用与经济学院,贵州 贵阳550025;2.贵州财经大学贵州省大数据统计与分析重点实验室,贵州 贵阳550025;3.天津财经大学统计学院,天津300000;4.贵州财经大学工商管理学院,贵州 贵阳550025;5.合肥工业大学管理学院,安徽 合肥230009
  • 收稿日期:2020-11-29 修回日期:2021-02-25 出版日期:2023-02-20 发布日期:2023-02-28
  • 通讯作者: 贾鸿业(1995-),男(汉族),河北石家庄人,天津财经大学统计学院,博士研究生,研究方向:大数据金融,Email:826066016@qq.com. E-mail:826066016@qq.com
  • 基金资助:
    贵州省大数据统计分析重点实验室(黔科合平台人才[2019]5103)

Credit Risk Warning of Listed Companies Based on Information Disclosure Text:Empirical Evidence from Management Discussion and Analysis of the Chinese Annual Report

LI Cheng-gang1, 2, JIA Hong-ye3, ZHAO Guang-hui4, FU Hong5   

  1. 1. School of Big Data Applications and Economics, Guizhou University of Finance and Economics, Guiyang 550025, China;2. Guizhou Key Laboratory of Big Data Statistics and Analysis, Guizhou University of Finance and Economics, Guiyang 550025, China; 3. School of Statistics, Tianjin University of Finance and Economics, Tianjin 300000, China;4. School of Business Administration, Guizhou University of Finance and Economics, Guiyang 550025, China;5. School of Management, Hefei University of Technology, Hefei 230009, China
  • Received:2020-11-29 Revised:2021-02-25 Online:2023-02-20 Published:2023-02-28
  • Contact: 贾鸿业 E-mail:826066016@qq.com

摘要: 本文运用文本挖掘技术,对2008-2018年1297家上市公司年报的管理层讨论与分析(MD&A)进行文本分析。从文本质量特征、文本词汇特征和文本语调特征等角度量化计算文本相似度、文本情感值、文本可读性三个维度文本披露指标,采用Logistic模型、决策树模型、支持向量机和神经网络模型四种方法构建上市公司信用风险预警模型,实证检验加入MD&A文本信息披露指标后信用风险预警模型的预测能力。实证结果表明:(1)在加入文本信息披露指标后,信用风险预警模型的预测准确度得到显著提升,多维度文本信息披露指标比单维度文本信息披露指标对信用风险预警模型预测准确度提升效果更优;(2)Logistic回归模型的预测准确度在样本数量较低时要优于决策树、支持向量机与神经网络,随着样本数量的增加,支持向量机和神经网络的预测准确度会明显提升;(3)不同特征的文本信息内容与企业是否发生信用风险均显著相关。本文的研究结论为提高信用风险预警的预测准确性提供了方法和经验证据,对于投资者与相关学者研究市场有效性提供新的研究视角。

关键词: 管理层讨论与分析;文本披露质量;文本挖掘;信用风险预警

Abstract: With the economic globalization, the international economic situation becomes more and more complex, and Chinese listed companies will face greater challenges. The unstable economic situation such as trade friction and financial market volatility will increase the credit risk of listed companies. The establishment of credit risk early warning system is conducive to the operators to find the company’s financial problems in time, and make response and prevention. A large number of text documents disclosed by listed companies can extract certain effective information, which can be used as an effective supplement to the traditional quantitative financial indicators. As an important part of the annual report, “Management Discussion and Analysis (MD & A)” in the enterprise annual report includes the evaluation of the company’s historical operation by the company’s managers and the prospect of the future market development. Therefore, deep mining the valuable text information contained in MD&A can effectively supplement the company’s financial index information and predict the company’s credit risk.

Key words: management discussion and analysis; text disclosure quality; text mining; credit risk warning

中图分类号: