A Hybrid CNN-LSTM Model for Enhancing Bond Default Risk Prediction

Authors
  • Jianhua Yao

  • Jiajing Wang

  • Bingxing Wang

  • Bingyao Liu

  • Mohan Jiang

Abstract

This paper explores the importance of credit risk management in the global financial market environment, especially for the prediction of bond default risk. With the advent of the big data era, the amount of market information has surged, covering multi-dimensional data from traditional financial statements to social media comments. However, traditional credit rating methods rely mainly on structured data and ignore the value of unstructured data, resulting in limited prediction accuracy. The development of deep learning technology provides a new way to process such data. By introducing a combined model of convolutional neural network (CNN) and long short-term memory network (LSTM), we propose a novel algorithm to predict bond default risk. The model uses CNN to process unstructured text data to extract key features and uses LSTM to process time series data to capture the trend of data changing over time. Experimental results show that the model performs well in terms of accuracy, surpassing other common models. The research in this paper provides new ideas for the application of deep learning in the financial field.

References
Cover Image
Downloads
Published
2024-09-30
Section
Articles
License
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Academic Scholar Hub Press also operates under the Creative Commons Licence CC-BY 4.0. This allows for copy and redistribute the material in any medium or format for any purpose, even commercially. The premise is that you must provide appropriate citation information.

How to Cite

Yao, J., Wang, J., Wang, B., Liu, B., & Jiang, M. (2024). A Hybrid CNN-LSTM Model for Enhancing Bond Default Risk Prediction. Journal of Computer Technology and Software, 3(6). https://doi.org/10.5281/zenodo.13910344

Most read articles by the same author(s)