计算机工程与应用2013，Vol.49Issue(5)：258-262,5.DOI:10.3778/j.issn.1002-8331.1110-0583
带权重的RBF神经网络银行个人信用评价方法
Method of personal credit evaluation of bank based on RBF neural network with weight
郭小燕 1张明2
作者信息
- 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
- 折叠
摘要
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.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Key words
based on weight/Radial Basis Function (RBF) neural network/pattern classification/credit evaluation分类
信息技术与安全科学引用本文复制引用
郭小燕,张明..带权重的RBF神经网络银行个人信用评价方法[J].计算机工程与应用,2013,49(5):258-262,5.
