Computer Engineering and Applications ›› 2013, Vol. 49 ›› Issue (5): 258-262.

Previous Articles     Next Articles

Method of personal credit evaluation of bank based on RBF neural network with weight

GUO Xiaoyan1, ZHANG Ming2   

  1. 1.School of Information and  Science Technology, Gansu Agriculture University, Lanzhou 730070, China
    2.School of Information Engineering, Lanzhou City University, Lanzhou 730070, China
  • Online:2013-03-01 Published:2013-03-14

带权重的RBF神经网络银行个人信用评价方法

郭小燕1,张  明2   

  1. 1.甘肃农业大学 信息科学技术学院,兰州 730070
    2.兰州城市学院 信息工程学院,兰州 730070

Abstract: A dynamic weighting cluster algorithm is proposed in this article in view of the problem of input sample’s classification weight being not considered by formerly RBF neural network. In this algorithm, the weighting distance replaces the Euclidean distance to act the role of measurement to the cluster. Based on this, the credit evaluation model is established, which is trained by  known category sample. Then the trained model is used to forecast the unknown category sample, the experimental result confirms the model’s validity.

Key words: based on weight, Radial Basis Function(RBF) neural network, pattern classification, credit evaluation

摘要: 针对RBF神经网络确定核函数中心时没有考虑输入样本分类指标权重的问题,提出了一种动态加权聚类算法。在算法中利用样本之间的加权距离代替了欧氏距离作为选定核函数中心的量度。在此基础上,建立了信用评价模型,利用已知类别的样本对模型进行训练,再利用训练好的模型对未知类别的样本进行预测,实验结果验证了模型的有效性。

关键词: 基于权重, 径向基函数(RBF)神经网络, 模式分类, 信用评价