构建基于PSO-BP网络的电信客户信用度评估模型

Construction of Credit Evaluation Model for Telecommunication Clients Based on PSO-BP Neural Network

随着中国电信行业的迅速发展,提高电信客户信用评估的准确度和科学性及其重要。文中针对BP神经网络的不足之处,研究了将粒子群算法应用于BP神经网络的优化问题,主要是将PSO算法运用于优化BP神经网络的权值,并通过对电信客户行为属性的统计分析,将其作为客户信用度预测评估的依据,建立了信用度评估模型,并用Matlab软件及其神经网络工具进行仿真和计算。实验表明,新模型采用的算法具有收敛速度快,预测精度高的优点,是一种有效的电信用户信用度评估模型。

With the rapid development of telecoms in China, it is very important to promote the accuracy and scientific of telecommunica tion clients＇credit rating. In this paper, the deficiency of Back Propagation （BP） neural network is optimized based on Panicle Swam Op timization （PSO） algorithm is studied aimed at the deficiency of BP neural network, PSO algorithm is used for optimizing parameters and threshold values of BP neural network. A credit evaluation model is built according to the statistic an＇,dysis of telecommunications clients ＂ behavior character. Matlab software and its neural network box is used to simulate and compute. The experiment results show that PSO -BP algorithm works with quicker convergence rate and the higher forecast precision. This model is a effective one which is content with the demand of credit evaluation of telecommunications clients.