Title: A study on corporate financial crisis prediction strategy based on particle swarm improved fuzzy clustering method from accounting perspective

Authors: Juan Ye

Addresses: Accounting Institute, Chongqing College of Finance and Economics, Chongqing, 402160, China

Abstract: The research focuses on improving the particle swarm algorithm and uses the improved particle swarm algorithm as a tool to optimise the probabilistic neural network and fuzzy clustering algorithm respectively. The results show that, in the comparison of homogeneous classifiers, the accuracy of the IFP model studied and designed has the highest broken line position, with the highest point reaching 88.76%, and the error rates in the first and second types of errors are 8.57% and 8.62% respectively, which are the lowest among similar models; It can be seen that the enterprise financial crisis prediction model designed in this study can guarantee higher prediction accuracy in practical application, help enterprises dynamically monitor their financial operation status in the operation process, real-time alert the coming financial crisis, and lay a theoretical foundation for a new enterprise financial monitoring system.

Keywords: particle swarm; fuzzy clustering; financial crisis; financial forecasting.

DOI: 10.1504/IJCSYSE.2023.132923

International Journal of Computational Systems Engineering, 2023 Vol.7 No.2/3/4, pp.177 - 189

Received: 30 Nov 2022
Accepted: 12 Mar 2023
Published online: 16 Aug 2023 *

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