Journal of Engineering, Project, and Production Management, 2026, 16(6), 2026-174
Integrating AOA and SVM for Multidimensional Identification and Prediction of Corporate Financial Risk
Lecturer, Department of Economic Management, Linyi Vocational University of Science and Technology, Linyi, 276000, China, E-mail: FangyuanGee@outlook.com
Project Management
Received February 3, 2026; revised March 25, 2026; accepted September 12, 2026
Available online September 20, 2026
Abstract: The current multidimensional identification and prediction methods for corporate financial risks heavily rely on manual experience, resulting in insufficient reliability of the results. To this end, a multidimensional identification and prediction model for enterprise financial risks is proposed by integrating arithmetic optimization algorithms and Support Vector Machine (SVM) to accurately predict enterprise financial difficulties. This study first uses indicator-screening algorithms to extract key indicators that reflect the financial status of enterprises from large volumes of financial data. Then, an arithmetic optimization algorithm is used to optimize the support vector machine model, which is combined with the extreme gradient boosting model to perform multidimensional identification and prediction of enterprise financial risks. The experimental results show that the model achieves recognition accuracy of 97.8%, F1 score of 92.7%, prediction accuracy of 98.4%, and a missed recognition rate of only 1.62%. In practical applications, the proposed model successfully identified 130 low-risk enterprises out of 135, with an overall prediction accuracy of 90.0%, significantly better than the comparison model. Experimental results show that this model has significant advantages in identifying and predicting financial risks in enterprises and can provide accurate, efficient support for enterprise risk management.
Keywords: Arithmetic optimization algorithm; support vector machine (SVM); corporate finance; risk identification; risk prediction; financial risk indicators.
Copyright © Journal of Engineering, Project, and Production Management (EPPM-Journal).
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.
Requests for reprints and permissions at eppm.journal@gmail.com.
Citation: Ge, F. (2026). Integrating AOA and SVM for Multidimensional Identification and Prediction of Corporate Financial Risk. Journal of Engineering, Project, and Production Management, 16(6), 2026-174.
