摘要
运用基于主分量分析和神经网络(PCA-NN)的个人信用评估模型以期取得更好的预测分类能力.经实证分析及与SVM方法、线性判别分析、Logistic回归分析、最近邻估计、分类回归树及神经网络等方法的对比,结果表明,该方法有很好的预测效果.
This paper applies principal components analysis and neural network to the credit scoring prediction problem in an attempt to suggest a new model with better classification accuracy. To evaluate the prediction accuracy of the model, we compare its performance with those of linear disciminating analysis, logistic regression analysis, K-nearest neighbors, classification and regression tree and neural network. The experiment results show the model have a very good prediction accuracy.
出处
《数学的实践与认识》
CSCD
北大核心
2007年第21期21-24,共4页
Mathematics in Practice and Theory
关键词
主分量分析
神经网络
信用评估
principal components analysis
neural network
credit scoring
