TY - JOUR
T1 - Deep learning models for bankruptcy prediction using textual disclosures
AU - Mai, Feng
AU - Tian, Shaonan
AU - Lee, Chihoon
AU - Ma, Ling
N1 - Publisher Copyright:
© 2018 Elsevier B.V.
PY - 2019/4/16
Y1 - 2019/4/16
N2 - This study introduces deep learning models for corporate bankruptcy forecasting using textual disclosures. Although textual data are common, it is rarely considered in the financial decision support models. Deep learning uses layers of neural networks to extract features from textual data for prediction. We construct a comprehensive bankruptcy database of 11,827 U.S. public companies and show that deep learning models yield superior prediction performance in forecasting bankruptcy using textual disclosures. When textual data are used in conjunction with traditional accounting-based ratio and market-based variables, deep learning models can further improve the prediction accuracy. We also investigate the effectiveness of two deep learning architectures. Interestingly, our empirical results show that simpler models such as averaging embedding are more effective than convolutional neural networks. Our results provide the first large-sample evidence for the predictive power of textual disclosures.
AB - This study introduces deep learning models for corporate bankruptcy forecasting using textual disclosures. Although textual data are common, it is rarely considered in the financial decision support models. Deep learning uses layers of neural networks to extract features from textual data for prediction. We construct a comprehensive bankruptcy database of 11,827 U.S. public companies and show that deep learning models yield superior prediction performance in forecasting bankruptcy using textual disclosures. When textual data are used in conjunction with traditional accounting-based ratio and market-based variables, deep learning models can further improve the prediction accuracy. We also investigate the effectiveness of two deep learning architectures. Interestingly, our empirical results show that simpler models such as averaging embedding are more effective than convolutional neural networks. Our results provide the first large-sample evidence for the predictive power of textual disclosures.
KW - Bankruptcy prediction
KW - Decision support systems
KW - Deep learning
KW - Machine learning
KW - Textual data
UR - http://www.scopus.com/inward/record.url?scp=85056216106&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85056216106&partnerID=8YFLogxK
U2 - 10.1016/j.ejor.2018.10.024
DO - 10.1016/j.ejor.2018.10.024
M3 - Article
AN - SCOPUS:85056216106
SN - 0377-2217
VL - 274
SP - 743
EP - 758
JO - European Journal of Operational Research
JF - European Journal of Operational Research
IS - 2
ER -