Title: Research on corporate financial risk prediction based on transformer models

Authors: Jiaqian Liu; Tiantian Qu; Huiting Wang; Jiayi Yu; Yi Fu

Addresses: School of Automotive Business, Hubei University of Automotive Technology, Shiyan, Hubei, 442002, China ' School of Automotive Business, Hubei University of Automotive Technology, Shiyan, Hubei, 442002, China ' School of Automotive Business, Hubei University of Automotive Technology, Shiyan, Hubei, 442002, China ' College of Industrial Management, Gyeongsang National University, Jinju, 52828, Korea ' Department of Management Information Systems, Gyeongsang National University, Jinju, 52828, South Korea

Abstract: Corporate financial risk prediction is crucial for economic stability and sustainable business operations, yet existing methods struggle with complex interdependencies among financial indicators and temporal dynamics. This study addresses the limitations of conventional approaches in handling high-dimensional financial data, weak temporal pattern recognition, and distributional rigidity across sectors by proposing a novel deep learning framework integrating graph transformer networks (GTN), time-series contrastive learning (TSCL) and meta-learning-based adaptive optimisation (Meta-AO). The hybrid architecture combines graph neural networks with transformer attention mechanisms to model enterprise relationships, employs contrastive learning for robust temporal pattern extraction, and utilises meta-learning for cross-domain adaptation. The findings establish that the proposed framework effectively captures relational structures, temporal dynamics, and distributional shifts in financial data, offering a comprehensive solution for accurate risk prediction across diverse market conditions and enterprise types through its hierarchical feature learning paradigm.

Keywords: financial risk prediction; transformer model; graph neural networks; GNNs; time-series contrastive learning; meta-learning; enterprise relationships; deep learning.

DOI: 10.1504/IJDSDE.2026.154409

International Journal of Dynamical Systems and Differential Equations, 2026 Vol.15 No.1, pp.37 - 70

Received: 07 Aug 2025
Accepted: 21 Nov 2025
Published online: 26 Jun 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article