Credit Card Customer Segmentation and Target Marketing Based on Data Mining

Based on the real data of a Chinese commercial bank’s credit card, in this paper, we classify the credit card customers into four classifications by K-means. Then we built forecasting models separately based on four data mining methods such as C5.0, neural network, chi-squared automatic interaction detector, and classification and regression tree according to the background information of the credit cards holders. Conclusively, we obtain some useful information of decision tree regulation by the best model among the four. The information is not only helpful for the bank to understand related characteristics of different customers, but also marketing representatives to find potential customers and to implement target marketing.