Customer segmentation of multiple category data in e-commerce using a soft-clustering approach

The segmentation of online consumers into multiple categories can contribute to a better understanding and characterization of purchasing behavior in the electronic commerce market. Online shopping databases consist of multiple kinds of data on customer purchasing activity and demographic characteristics, as well as consumption attributes such as Internet usage and satisfaction with services. Information about customers uncovered by segmentation enables company administrators to establish good customer relations and refine their marketing strategies to match customer expectations. To achieve optimal segmentation, we developed a soft clustering method that uses a latent mixed-class membership clustering approach to classify online customers based on their purchasing data across categories. A technique derived from the latent Dirichlet allocation model is used to create the customer segments. Variational approximation is leveraged to generate estimates from the segmentation in a computationally-efficient manner. The proposed soft clustering method yields more promising results than hard clustering and greater within-segment clustering quality than the finite mixture model. (C) 2010 Elsevier B. V. All rights reserved.