Deep learning models for bankruptcy prediction using textual disclosures

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.