Papers by Keyword: Customer Segmentation

Abstract: With the rising growth of electronic commerce (EC) customers, EC service providers are keen to analyze the on-line browsing behavior of the customers in their web site and learn their specific features. Clustering is a popular non-directed learning data mining technique for partitioning a dataset into a set of clusters. Although there are many clustering algorithms, none is superior for the task of customer segmentation. This suggests that a proper clustering algorithm should be generated for EC environment. In this paper we are concerned with the situation and proposed an improved k-means algorithm, which is effective to exclude the noisy data and improve the clustering accuracy. The experimental results performed on real EC environment are provided to demonstrate the effectiveness and feasibility of the proposed approach.

Abstract: Application of data mining in mobile communication enterprises can help the enterprises conduct customers subdivision, understand characteristics of consumer behavior and develop appropriate product service systems based on different subdivided groups to occupy more market shares and provide better services for customers. By applying cluster analysis method in data mining and using k-means algorithm, this paper analyzes the collected mobile service consumption data with college students as samples, concludes behavioral characteristics of the mobile service consumption of three type college students and makes proposals from the perspective of operators.

Abstract: In this article, it provided one way to build Customer Centered data sheet based on RFM for online shopping, then with K-Means algorithm in SAS EM, succeeded in clustering the samples. That was meaningful for further study on characteristics of every segment. At the end, the writer summarized the meaning of customer segmentation and inadequate of the model.

Abstract: This paper uses the clustering model SOM-Kmeans two segment to cluster the users on railway ticket selling system. First, it describes the types of customer segmentation and the general segmentation steps, then introduces the definition of user preferences, at last on the basis of calculation steps of SOM-Kmeans two segment algorithm, the customer segmentation model and algorithm is given based on user preferences.

Abstract: The This paper studies bank customers segmentation problem. Improved Apriori mining algorithm is a kind of data mining technology which is an important method in bank customers segmentation. In practical application, the traditional algorithm has shortcomings of the initial values sensitive and easy to fall into local optimal value, which will lead to low accuracy rate of silver class customer classification. According to the shortcomings of traditional algorithm, this paper puts forward a bank customer segmentation method based on improved Apriori mining algorithm in order to improve the bank customer segmentation accuracy. Experimental results show that the algorithm can effectively overcome the traditional algorithms shortcomings of easy to fall into local optimal value, improve the customer classification accuracy, make mining results more reasonable, lay down different customer service strategies for different client base, improve effective reference opinions of bank decision makers, and bring more benefits for the bank.

Abstract: Market competition is the competition for customers. By adopting customer segmentation model, decision makers can effectively identify valuable customers and then develop effective marketing strategy. Cluster analysis is one of the major data analysis methods and the k-means clustering algorithm is widely used. But the original k-means algorithm is computationally expensive and the quality of the resulting clusters heavily depends on the selection of initial centroids. An improved K-means algorithm is presented,with which K value of clustering number is located according to the clustering objects distribution density of regional space,and it uses centroids of high-density region as initial clustering center points. The proposed method makes the algorithm more effective and efficient, so as to gets better clustering with reduced complexity.

Abstract: Segmentation based on customer value and needs can better guide marketing decision-making of airlines as well as better understand needs of high-value passengers. To address customer segmentation in Customer Relationship Management (CRM), the paper proposed and designed airline customer segmentation system structure based on ant colony clustering. The key ant colony clustering algorithm was also designed and implemented. The ant colony clustering algorithm mainly used adaptively adjusted group similarity to perform clustering and access to initial clustering result. Then all data representation points and abnormal data were inputted into lattice plane scattered randomly. Ant colony algorithm was used for clustering once again and corresponding class label was used to delete abnormal values and obtain complete clusters. Data test example based on ant colony clustering customer analysis platform illustrated its feasibility and effectiveness

Abstract: Nowadays, with the rapid development of technology and the rapid popularization of Internet applications, many Chinese businesses are attracted by huge profits and market space of e-commerce, beginning to join the area of e-commerce. How to keep effective customer, attract more members of the e-commerce website and expand the market effectively, is the problem that all the managers most concerned about. Through studying and comparing common customer segmentation models, this article is proposing a integrated model that combines the techniques of generalized association rules and decision tree. This model is used for customer segmentation for e-commerce websites. It can help managers understand customers, develop markets, and support decision-making.