消费者信用评估中支持向量机方法研究  

Support Vector Machines Approach to Credit Evaluation

作　　者：李建平[1] 徐伟宣[1] 刘京礼[1] 石勇[2] 

机构地区：[1]中国科学院科技政策与管理科学研究所,北京100080 [2]中国科学院研究生院,北京100039

出　　处：《系统工程》2004年第10期35-39,共5页Systems Engineering

基　　金：国家杰出青年基金资助项目(70028101);中国科学院院长基金资助项目(yjjz946);中国科学院科技政策与管理研究所所长基金资助项目(0343sz)

摘　　要：消费者信用评估是金融与银行界研究的重要内容,最近的研究显示统计学习理论(SLT)方法在信用评估中有优势。本文在信用评估中应用了一种新的方法——支持向量机方法(SVM),该方法属于机器学习理论发展的最新阶段,具有专门针对有限样本、算法复杂度与样本维数无关等优点。使用真实的信用卡数据实证结果表明,本方法具有较好的预测能力,在与国内某商业银行现有信用卡个人信用评估方法的对比研究中,该方法具有明显的优势。Credit assessment has attracted lots of researchers in financial and banking industry. Recent studies have shown (that) Statistic Learning Theory(SLT) methods are competitive to statistical methods for credit assessment. This article (applies) support vector machines(SVM), a relatively new machine learning technique, to the credit assessment problem for (better) explanatory power. The structure of SVM has many computation advantages, such as special direction at a finite (sample) and irrelevance between the complexity of algorithm and the sample dimension. A real credit card data experiment (shows) that SVM method has outstanding assessment ability. Compared with the method that is currently used by a major (Chinese) bank, the SVM method has a great potential superiority in predicting accuracy.

关 键 词：信用评估 分类 支持向量机 SVM 

分 类 号：F830[经济管理—金融学]