Narrow Results

Customer classification is one of the major tasks in customer relationship management. Customers often have both static characteristics and dynamic behavioral features. Using both kinds of data to conduct comprehensive analysis can enhance the reasonability of customer classification. In the proposed classification method, customer dynamic data is clustered using a hybrid genetic algorithm. The result is then combined with customer static data to give reasonable customer segmentation supported by neural network technique. A bank dataset-based experiment shows that applying the proposed method can obviously improve the accuracy of customer classification comparing with the traditional methods where only static data is used.