Journal of Risk Model Validation

Risk.net

Incorporating financial reports and deep learning for financial distress prediction: empirical evidence from Chinese listed companies

Jiaming Liu, Ming Jia, Yanan Hao and Lu Wang

  • This paper explores the use of textual data from financial reports for predicting financial distress in Chinese listed companies. It proposes models incorporating Word2Vec and BERT for text embedding to capture sentiment and tone from the texts.
  • The study compares different text embedding methods, including word2vec-averaging, word2vec-weighting, BERT-word, and BERT-sentence, to examine their effectiveness in improving the predictive performance of financial distress models.
  • The paper also investigates the combination of textual features with traditional financial indicators for enhanced prediction accuracy. Results show that the inclusion of textual features can improve the discriminability of predictions, especially over longer prediction horizons.

This study conducts a comparative study on text information processing methods for financial distress prediction. Word2vec and bidirectional encoder representations from transformers (BERT) are employed to convert financial reports into vectors. Weighted word2vec and BERT-sentence are also used for enhanced text processing and report quantification. Experimental results based on a data set of 62 312 Chinese listed companies from 2000 to 2021 show that weighted word2vec achieves an average prediction accuracy of 85.27% in cross-validation and 84.67% in sliding-time- window validation. The findings indicate that incorporating semantic information from management discussion and analysis (MD&A) significantly improves the performance of distress prediction models for listed companies, regardless of the text-processing technique used. Text-based features become comparable with financial indicators and even surpass them as the prediction horizon extends. Combination features offer greater enhancement than financial indicators, especially for longer prediction horizons. We therefore offer a comprehensive validation of the MD&A for the purpose of predicting financial distress, and we firmly believe that it serves as a valuable tool in mitigating risk within financial risk management.

Sorry, our subscription options are not loading right now

Please try again later. Get in touch with our customer services team if this issue persists.

New to Risk.net? View our subscription options

Want to know what’s included in our free membership? Click here

You need to sign in to use this feature. If you don’t have a Risk.net account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here