Research on the Pre-warning Model of Enterprise Financial Crisis Based on the Information Entropy and PSO-ANN

摘要

The pre-warning of enterprise financial crisis is a hot studying spot in current theoretical field. This paper firstly overviews the present research conditions of enterprise financial crisis pre-warning, sets up a more perfect pre-warning indicators system. Then accomplishes dynamic pre-warning for the financial risk based on the great nonlinear function approaching capability of artificial nerve network(ANN). To simplify the space dimension of input information and reduce the complexity of network structure, the information entropy reduction theory is brought in. At the same time, aim at the main shortage of ANN (the converging speed is often slow and the network is easily involved in local optimum), this paper introduces the Particle Swarm Optimization(PSO). Thus establishing a pre-warning system to enterprise financial crisis based on the information entropy and the PSO-ANN, making the information reduction, the dynamic study and induction of ANN, the particle swarm optimization, the forecast and evaluation of enterprise financial crisis organically combined. At last, an actual example is given to justify the validity and efficiency of this model. The study can supplies a new means for the dynamic pre-warning of enterprise financial crisis.