EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-modal deep learning for credit rating prediction using text and numerical data streams

Mahsa Tavakoli, Rohitash Chandra, Fengrui Tian, Cristián Bravo

Applied Soft Computing · 2025-03 · 171 · 112771

DOI: 10.1016/j.asoc.2025.112771 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Soft Computing, 2025-03. Verfasst von Mahsa Tavakoli und 3 weiteren Autor:innen. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 118 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Alliance de recherche numérique du Canada, NSERC, National Research Council Canada.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Knowing which factors are significant in credit rating assignment leads to better decision-making. However, the focus of the literature thus far has been mostly on structured data, and fewer studies have addressed unstructured or multi-modal datasets. In this paper, we present an analysis of the most effective architectures for the fusion of deep learning models for the prediction of company credit rating classes, by using structured and unstructured datasets of different types. In these models, we tested different combinations of fusion strategies with different deep learning models, including CNN, LSTM, GRU, and BERT. We studied data fusion strategies in terms of level (including early and intermediate fusion) and techniques (including concatenation and cross-attention). Our results show that a CNN-based multi-modal model with two fusion strategies outperformed other multi-modal techniques. In addition, by comparing simple architectures with more complex ones, we found that more sophisticated deep learning models do not necessarily produce the highest performance; however, if attention-based models are producing the best results, cross-attention is necessary as a fusion strategy. Finally, our comparison of rating agencies on short-, medium-, and long-term performance shows that Moody's credit ratings outperform those of other agencies like Standard&Poor's and Fitch Ratings.

Förderung

  • Alliance de recherche numérique du Canada
  • NSERC
  • National Research Council Canada
  • Canada Research Chairs
  • Compute Canada

Zitieren

APA

Tavakoli, M., Chandra, R., Tian, F., & Bravo, C. (2025). Multi-modal deep learning for credit rating prediction using text and numerical data streams. Applied Soft Computing, 171, 112771. https://doi.org/10.1016/j.asoc.2025.112771

Vancouver

Tavakoli M, Chandra R, Tian F, Bravo C. Multi-modal deep learning for credit rating prediction using text and numerical data streams. Applied Soft Computing. 2025;171:112771. doi:10.1016/j.asoc.2025.112771

BibTeX
@article{Tavakoli2025,
  author = {Tavakoli, Mahsa and Chandra, Rohitash and Tian, Fengrui and Bravo, Cristián},
  title = {Multi-modal deep learning for credit rating prediction using text and numerical data streams},
  journal = {Applied Soft Computing},
  year = {2025},
  volume = {171},
  pages = {112771},
  doi = {10.1016/j.asoc.2025.112771}
}
Kostenlos starten →