文档介绍：论文题目:基于数据挖掘的信用卡个人客户信用评价研究
专业:管理科学与工程
硕士生:聂雨(签名):
指导老师:苏建军(签名):
摘要
自上个世纪 90 年代以来,随着中国经济的发展和内需的扩大,信用卡业务迅速发
展起来。信用卡业务的关键在于信用风险的控制,为了更好的防范信贷风险和进一步推
动个人消费信贷业务的发展,发卡机构必须建立一套完善有效、科学合理的个人信用评
价体系。信用评价将客户分为“好”客户和“差”客户,根据历史上每个属性的若干样
本,建立数学模型,预测信用卡使用者的违约风险。决策树算法简单直观,误差率低,
本文选取该算法作为建立信用评价模型的方法。
本文首先对数据挖掘、信用卡业务、信用评价三者的理论框架进行结合,分析了数
据挖掘、信用卡业务中信用评价的特点,为下文建模方法的筛选奠定理论基础。其次结
合数据挖掘几种方法的不同特性,选择决策树算法作为本文模型建立方法,并详
细介绍了如何利用算法建立模型。最后从某发卡行获取的商业银行信用卡个人数
据出发,采用上述算法,经过商业理解、数据理解、数据准备、建立模型、模型评估与
分析等步骤,建立了个人信用评价的决策树模型。并且依据发卡机构的实际需求,对决
策树模型的成本矩阵和修剪程度进行了调整,形成了修正改进的模型。
基于决策树方法的个人信用评价模型精确度高、可控性强,可在实际中广泛运用。
且通过建立误判矩阵,使得发卡机构运营中成本最低。在实际运用中对于进行信用卡申
请者的判别有一定的指导性作用,并能够为信贷决策提供支持,具有较强的理论和现实
意义。

关键词:数据挖掘;决策树;;信用卡
研究类型:应用研究
Subject : Research on Credit Rating of Consumer client of Credit
Card based on Data Mining
Specialty : Management Science and Engineering
Name : Nie Yu (Signature)
Instructor : Su Jianjun (Signature)
ABSTRACT
Since. the 90’s, with the development of China's economy and the expansion of domestic demand,
Credit Card Industry developed rapidly. The key of Credit Card Industry is control of credit risks. In
order to guard against credit risks efficiently, to promote the development of the consumer credit
business, card issuers must establish a set of effective scientific and reasonable individual credit system.
The credit rating system divided customers into “good” customers and ”bad” customers. Then according
to the historical data of different attributes, set a mathematical model, forecast the default risk of credit
card users. Decision Trees is simple, easily understanding and has low error rate, so this paper take the
algorithm as the modeling method.
Firstly, this bines data mining, credit card industry, credit rating together, analyzed the
characteristics of data mining and credit rating for credit card, lay a theoretical foundation for the
following discussion. Secondly, consider the different feature