EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Corporate financial distress prediction with multiperiod annual report data: A fusion deep neural network model

Chongren Wang, Pimei Gong iD, Jiawang Li, Zhiyi Wang

PLOS One · 26.09.2025 · 20 (9) · e0333064

DOI: 10.1371/journal.pone.0333064 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 26.09.2025. Verfasst von Chongren Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Management Science and Engineering, Shandong University of Finance and Economics, Jinan, China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Financial Stress. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shandong Province Science and Technology-based Small and Medium-sized Enterprises Innovation Capacity Enhancement Project, Jinan City School Integration Development Strategy Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The occurrence of financial distress in enterprises not only leads to operational difficulties but also may trigger chain reactions such as bankruptcy, debt arrears, layoffs, etc., which in turn have a negative effect on investors, creditors, and the entire economic system. Therefore, accurately and timely predicting the financial distress of enterprises is highly important. To address this, a fusion deep neural network based on multiple annual report text data and financial data (MTF-FDNN) model is proposed for financial distress prediction. This model can simultaneously extract long text features of multiple annual reports and financial indicator features of multiple periods of enterprises. Specifically, the model first constructs a multiperiod financial feature extraction model on the basis of a fully connected neural network. Next, it uses a fine-tuned longformer pretrained model to convert long texts into vector representations. Subsequently, Bi-LSTM and TextCNN are employed to extract semantic features from long texts both globally and locally. Finally, the fused financial features and semantic features of long texts are used to identify the financial distress of listed companies. Additionally, on the basis of the experimental results from the test set, the proposed model demonstrates significant improvements over traditional multiperiod financial indicator-based prediction models, with increases of 4.98% in AUC, 6.54% in accuracy, 10.58% in recall, and 6.48% in the F1 score. It is evident that introducing multiperiod textual features significantly enhances model predictive performance. This model effectively predicts corporate financial distress, thereby assisting business managers, external investors, and other stakeholders in mitigating risk.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerFinancial StressHumansModels, EconomicInvestmentsFinancial Management

Autor:innen und Institutionen

  • School of Management Science and Engineering, Shandong University of Finance and Economics, Jinan, China.
  • Digital Economy Research Institute, Shandong University of Finance and Economics, Jinan, China.

ORCID-Profile: Pimei Gong

Förderung

  • Shandong Province Science and Technology-based Small and Medium-sized Enterprises Innovation Capacity Enhancement Project
  • Jinan City School Integration Development Strategy Project

Zitieren

APA

Wang, C., Gong, P., Li, J., & Wang, Z. (2025). Corporate financial distress prediction with multiperiod annual report data: A fusion deep neural network model. PLOS One, 20(9), e0333064. https://doi.org/10.1371/journal.pone.0333064

Vancouver

Wang C, Gong P, Li J, Wang Z. Corporate financial distress prediction with multiperiod annual report data: A fusion deep neural network model. PLOS One. 2025;20(9):e0333064. doi:10.1371/journal.pone.0333064

BibTeX
@article{Wang2025,
  author = {Wang, Chongren and Gong, Pimei and Li, Jiawang and Wang, Zhiyi},
  title = {Corporate financial distress prediction with multiperiod annual report data: A fusion deep neural network model},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {9},
  pages = {e0333064},
  doi = {10.1371/journal.pone.0333064}
}
Kostenlos starten →