Application Of Data Mining In The Bank Credit

With the increasing needs for enhancing management level and the development ofsoftware, some banks are developing a comprehensive information system that integratesinternal control, operation management, finance and costing control and decisionanalyses. With the support from data mining technique and other relevant tools, bank istrying to establish a comprehensive management bank system, which will be beneficial toset up its core competence; to mitigate risk, thus to realize profit maximization.This thesis analyzes the present situation of data management and application inChina’ banking industry; summarizes the construction approaches of subject-orientedbanking data warehouse; discusses the construction methods of system models ofcustomer classification, risk prediction and performance evaluation on the demandbackground of China Construction Bank X branch. This thesis uses Microsoft SQLServer2000and Analysis Services data warehouse solutions. In the system of customerclassification and risk prediction, we use method of MS Decision Tree provided byAnalysis Services to generate decision tree. Through this decision tree, a simpleprediction strategy can form. To apply the rule on judgment on new customers, it wouldbe quick to have a rough result on classification, thereby to predict risk. This thesis usedClementine offered by SPSS to test the effectiveness of this system, used CART and C5.0decision tree algorithm, and then make machine learning to bank credit approval,generated two rule sets.