Artificial intelligence-driven financial risk assessment: A deep learning-based credit scoring method for manufacturing enterprises
DOI:
https://doi.org/10.4108/eetsis.14324Keywords:
financial risk assessment of manufacturing enterprises, industry disturbance, financial sensisitivity, conditioned exposure, matching consistencyAbstract
Financial risk assessment for manufacturing enterprises supports credit-risk screening and early warning. Existing methods often fuse multi-period financial and industry information through concatenation, shared representations, or unrestricted interactions, making it difficult to separate meaningful disturbance–sensitivity correspondences from irrelevant combinations. This study proposes an industry-disturbance-conditioned credit-scoring framework. Its originality lies in explicitly matching external disturbances with firm-level financial sensitivities rather than treating them as unrestricted features. The framework decomposes financial information into levels, intertemporal changes, and accounting divergences; constructs demand, cost, and production sensitivities; and estimates conditioned exposures through a correspondence matrix and conditional gates. A matching-consistency loss constrains disturbance–sensitivity relationships, while dual-path prediction retains exposure-related and firm-specific risk information. Using Moody’s Orbis and Eurostat Short-Term Business Statistics (STS), the method achieves an AUPRC of 0.512 in the full out-of-time test, exceeding TabPFN, the strongest AUPRC baseline, by 1.4 percentage points. Its AUROC is 0.879, and its FNR of 0.276 is lower than 0.289 for HGNN and 0.291 for TabPFN. Among highly sensitive firms, the proposed model achieves an AUPRC of 0.489 and an FNR of 0.288, improving on HGNN by 1.5 and 2.3 percentage points, respectively. Statistical tests, ablation studies, and repeated runs support the matching and prediction mechanisms. Independent calibration further reduces probability error and calibration bias. The framework supports relative risk ranking and distress screening during industry disturbances, although validation across additional databases and disturbance settings remains necessary.
References
[1] Jiang, Q., Wang, N., Jiang, B., & Bu, F. (2026). Relationship between supply chain disruption orientation and firm’s resilience in China: the dynamic capabilities perspective. Asia Pacific Business Review, 32(1), 62-89.
[2] Flannery, M. J., & Öztekin, Ö. (2024). Working capital balances and financial policy. Journal of Corporate Finance, 87, 102618.
[3] Cheng, S. F., Vyas, D., Wittenberg-Moerman, R., & Zhao, W. (2025). Exposure to superstar firms and financial distress. Review of Accounting Studies, 30(2), 1355-1396.
[4] Lokanan, M. E., & Ramzan, S. (2024). Predicting financial distress in TSX-listed firms using machine learning algorithms. Frontiers in Artificial Intelligence, 7, 1466321.
[5] Wang, M., Huang, W., Xie, W., Hou, J., Gao, X., & Fu, X. (2026). TemFRC: Enterprise financial risk prediction with temporal folding and risk contrast. Information Processing & Management, 63(7), 104780.
[6] Beade, Á., Rodríguez, M., & Santos, J. (2024). Business failure prediction models with high and stable predictive power over time using genetic programming. Operational Research, 24(3), 52.
[7] Liu, J., & Jia, M. (2025). Financial distress prediction with annual reports-based deep textual feature extraction: A hybrid approach. Information Sciences, 686, 121318.
[8] Wu, C., Jiang, C., Wang, Z., & Ding, Y. (2024). Predicting financial distress using current reports: A novel deep learning method based on user-response-guided attention. Decision Support Systems, 179, 114176.
[9] Abdelkader, N. A. M., & Wahba, H. H. (2024). A proposed multidimensional model for predicting financial distress: an empirical study on Egyptian listed firms. Future Business Journal, 10(1), 42.
[10] Che, W., Wang, Z., Jiang, C., & Abedin, M. Z. (2024). Predicting financial distress using multimodal data: An attentive and regularized deep learning method. Information Processing & Management, 61(4), 103703.
[11] Altman, E. I. (1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The journal of finance, 23(4), 589-609.
[12] Ohlson, J. A. (1980). Financial ratios and the probabilistic prediction of bankruptcy. Journal of accounting research, 18(1), 109-131.
[13] Borisov, V., Leemann, T., Seßler, K., Haug, J., Pawelczyk, M., & Kasneci, G. (2024). Deep neural networks and tabular data: A survey. IEEE Transactions on Neural Networks and Learning Systems, 35(6), 7499–7519.
[14] Zhao, J., Ouenniche, J., & De Smedt, J. (2024). Survey, classification and critical analysis of the literature on corporate bankruptcy and financial distress prediction. Machine learning with applications, 15, 100527.
[15] Nguyen, M., Nguyen, B., & Liêu, M. L. (2024). Corporate financial distress prediction in a transition economy. Journal of Forecasting, 43(8), 3128-3160.
[16] du Jardin, P. (2025). A Quantification Approach of Changes in Firms' Financial Situation Using Neural Networks for Predicting Bankruptcy. Journal of Forecasting, 44(2), 781-802.
[17] Thor, M., & Postek, Ł. (2024). Gated recurrent unit network: A promising approach to corporate default prediction. Journal of Forecasting, 43(5), 1131-1152.
[18] 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.
[19] Rahmi, A., Lu, C. C., Liang, D., & Fadilah, A. N. (2024). Splitting long‐term and short‐term financial ratios for improved financial distress prediction: Evidence from Taiwanese public companies. Journal of Forecasting, 43(7), 2886-2903.
[20] El Madou, K., Marso, S., El Kharrim, M., & El Merouani, M. (2024). Evolutions in machine learning technology for financial distress prediction: A comprehensive review and comparative analysis. Expert Systems, 41(2), e13485.
[21] Huang, M. N., & Lee, H. H. (2024). Inter-industry network and credit risk. International Review of Economics & Finance, 92, 598-625.
[22] Huang, Y., Wang, Z., & Jiang, C. (2024). Diagnosis with incomplete multi-view data: A variational deep financial distress prediction method. Technological Forecasting and Social Change, 201, 123269.
[23] Liu, Z., Luo, Y., & Duan, M. (2025). Macroeconomic factors, industrial enterprises, and debt default prediction: Based on the VAR-GRU model. Finance Research Letters, 78, 107122.
[24] Qiu, G., Kuang, D., & Goel, S. (2024, July). Complexity matters: feature learning in the presence of spurious correlations. In Forty-first International Conference on Machine Learning.
[25] Kim, C., Van Der Schaar, M., & Lee, C. (2024, July). Discovering features with synergistic interactions in multiple views. In Forty-first International Conference on Machine Learning.
[26] Wu, S. L., Du, L., Yang, J. Q., Wang, Y. A., Zhan, D. C., Zhao, S., & Sun, Z. X. (2024). RE-SORT: Removing spurious correlation in multilevel interaction for CTR prediction. In Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence (pp. 3816–3828).
[27] Song, Y., Jiang, M., Li, S., & Zhao, S. (2024). Class‐imbalanced financial distress prediction with machine learning: Incorporating financial, management, textual, and social responsibility features into index system. Journal of Forecasting, 43(3), 593-614.
[28] Hu, Y. H., Tsai, C. F., & Wang, P. T. (2025). Combining multiple data resampling methods and classifier ensembles for better financial distress prediction: homogeneous and heterogeneous approaches. Annals of Operations Research, 353(2), 793-814.
[29] Guilbert, T., Caelen, O., Chirita, A., & Saerens, M. (2024). Calibration methods in imbalanced binary classification. Annals of Mathematics and Artificial Intelligence, 92(5), 1319-1352.
[30] Nassiri, V., Tekle, F., Tatikola, K., & Geys, H. (2024). Addressing class imbalance in Bayesian classification through posterior probability adjustment. Biometrical Journal, 66(8), e70004.
[31] Yang, M., & Bi, X. (2025). Cost-Aware Calibration of Classifiers. INFORMS Journal on Data Science, 4(2), 101-113.
[32] Gnip, P., Kanasz, R., Zoričak, M., & Drotar, P. (2025). An experimental survey of imbalanced learning algorithms for bankruptcy prediction. Artificial Intelligence Review, 58(4), 104.
[33] Hu, Z., Dong, Y., Wang, K., & Sun, Y. (2020, April). Heterogeneous graph transformer. In Proceedings of the web conference 2020 (pp. 2704-2710).
[34] Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).
[35] Wang, R., Shivanna, R., Cheng, D., Jain, S., Lin, D., Hong, L., & Chi, E. (2021, April). Dcn v2: Improved deep & cross network and practical lessons for web-scale learning to rank systems. In Proceedings of the web conference 2021 (pp. 1785-1797).
[36] Gorishniy, Y., Rubachev, I., Kartashev, N., Shlenskii, D., Kotelnikov, A., & Babenko, A. (2024). TabR: Tabular deep learning meets nearest neighbors. In International Conference on Learning Representations.
[37] Xiao, J., Liu, R., & Dyer, E. (2024, May). GAFormer: Enhancing timeseries transformers through group-aware embeddings. In International Conference on Learning Representations.
[38] Luo, D., & Wang, X. (2024, May). ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis. In ICLR.
[39] Hollmann, N., Müller, S., Eggensperger, K., & Hutter, F. (2023). Tabpfn: A transformer that solves small tabular classification problems in a second. In International Conference on Learning Representations.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Shiliang Chang
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
