The Research of University Financial Performance Evaluation Based on PCA and PSO MLP Network

Abstract

The evaluation of university financial performance evaluation is a complex system. Domestic and foreign scholars generally agreed that the evaluation of university financial performance is a difficult task. In this paper, a new evaluation model with principal component analysis (PCA) and particle swarm optimization (PSO) neural network is founded based on the comprehensive evaluation index system of university financial performance evaluation. A neural network model to the problem is trained by particle swarm optimization technique, which is a new adaptive algorithm based on a social-psychological metaphor, using principal component analysis to extract availability information and to solve a principal component. After empirical research with MATLAB7.0, we find that both the convergence speed and the evaluation accuracy are enhanced in comparison with the traditional neural network model.