|
Activity Number:
|
423
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistical Learning and Data Mining
|
| Abstract - #303566 |
|
Title:
|
An Empirical Application of Credit Card Customers' Classification and Recognition in a Chinese Bank
|
|
Author(s):
|
Li Xia*+ and Bin Zhang and Ming Xie and Minglu Li and Jinyan Shao and Lili Zhao
|
|
Companies:
|
IBM China Research Laboratory and IBM China Research Laboratory and IBM China Research Laboratory and IBM China Research Lab and IBM China Research Lab and IBM China Research Lab
|
|
Address:
|
Diamond Building, Zhongguancun Software Park, Beijing, International, 100193, China
|
|
Keywords:
|
customer classification ; valuable customer recognition ; decision tree classification ; customer behavior pattern recognition ; credit card customer
|
|
Abstract:
|
Customer classification is important for banks to explore the market. In this paper, we study the transaction data of credit card business of one of the largest banks in China. The database has more than 60,000 credit card holders' information and more than 200,000 transaction records. In order to achieve a good classification result, several classification methods are compared. The comparison results demonstrate that the decision tree classification method is a feasible model for credit card customer analysis. This method is based on the customer contribution to banks and customer behavior pattern. From the results of decision tree classification method, some useful rules can be derived to help banks find the valuable customers and design customized products. These results are meaningful for banks to improve the profitability and competitive power of credit card business.
|
