Hybrid PSO-SVM for Financial Early-Warning Model of Small and Medium-Sized Enterprises

Xinke Chong
2021 Proceedings of the 6th International Conference on Financial Innovation and Economic Development (ICFIED 2021)   unpublished
As feature subset selection and parameter tuning are important for the performance of SVM-based models, a PSO-SVM model was provided which uses particle swarm optimization (PSO) to optimize both a feature subset and parameters of SVM simultaneously so as to improve the prediction result. Finally, the PSO-SVM model was applied to a financial early warning model, which shows a better performance than the pure SVM-based model.
doi:10.2991/aebmr.k.210319.020 fatcat:w5v467l22zctxmzuns4tllokgq