Bank Customer Classification Model Based on Elman Neural Network Optimized by PSO

Bank customer classification plays an important role for commercial banks to keep away from default risks in customer loan market. This paper constructs a bank customer classification model based on Elman neural network Aiming at the insufficiency of BP algorithm used in standard Elman neural network, this paper combines the PSO algorithm and the Elman neural network to construct a PSO-Elman neural network by using PSO as the training method. The model was used in bank customer classification based on customer loan data from one commercial bank Compared with the standard Elman network trained by BP algorithm, the application results indicate that PSO-Elman network gets higher classification accuracy on testing samples and performs better on robustness.