Research on Financial Risk of Chinese Manufacturing Listed Companies Based on SVM

Yuan Yan; Xiahui Che

Authors

Yuan Yan Graduate School, Jose Rizal University, Manila 0900, Philippines
Xiahui Che School of Management Science and Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China

Abstract

Financial crisis early warning is of great significance for the company's management, investors, and government regulators to make correct crisis identification. Up to now, many scholars at home and abroad have used neural networks, support vector machines, and logistic regression to conduct financial crisis early warning research on listed companies and have obtained many valuable research results. However, for the financial crisis early warning of listed companies in China's manufacturing industry, there is no financial crisis early warning model that considers non-financial indicators such as the nature of equity and the nature of EVA. This article takes the manufacturing companies listed on the Shanghai and Shenzhen A-share mainboards as a sample, uses principal component analysis to reduce dimensionality, and selects 7 indicators from 30 financial and non-financial indicators as typical indicators of financial crisis early warning, the establishment of SVM, Logistic and KNN three model algorithms for empirical research, the research results found: return on assets, total asset net profit rate, quick ratio, fixed asset turnover rate, total asset turnover rate, cash re The investment ratio and the total asset EVA ratio accounted for 81.427% of the predicted financial crisis. The first three years of these indicators data can be used to judge whether the company will have a financial crisis. At the same time, it also proves that the support vector machine has a better financial early warning ability

References

Almamy, J., Aston, J., & Ngwa, L. N. (2016). An evaluation of Altman's Z-score using cash flow ratio to predict corporate failure amid the recent financial crisis: Evidence from the UK. Journal of Corporate Finance, 36, 278-285.

Altman, E. I. (1968). FINANCIAL RATIOS, DISCRIMINANT ANALYSIS AND THE PREDICTION OF CORPORATE BANKRUPTCY. Journal of Finance, 23(4), 589-609.

Beaver, W. H. (1966). Financial ratios as predictors of failure. Journal of accounting research, 71-111.

Fan, A., & Palaniswami, M. (2000). Selecting bankruptcy predictors using a support vector machine approach. Paper presented at the Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

Fitzpatrick, P. J. (1932). A Comparison of the Ratios of Successful Industrial Enterprises with Those of Failed Companies.

Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006). A fast learning algorithm for deep belief nets. Neural computation, 18(7), 1527-1554.

Martin, D. (1977). Early warning of bank failure: A logit regression approach. Journal of banking & finance, 1(3), 249-276.

Min, J. H., & Lee, Y.-C. (2005). Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters. Expert systems with applications, 28(4), 603-614.

Ohlson, J. A. (1980). Financial ratios and the probabilistic prediction of bankruptcy. Journal of accounting research, 109-131.

Sun, x. (2013). Dynamic Early Warning Model Based on a Financial Distress State Space:An Empirical Study in China. Chinese soft science(4), 8.

Vapnik, V. (1999). The nature of statistical learning theory: Springer science & business media.

Xiaoyan, W., & Jiahan, Y. (2020). Financial risk early warning model with penalty constraint based on cluster analysis. Statistics and Decision making(2), 4.