Customer clustering and pattern identification approach based on vague C-means

In the mass customization production, customer clustering and identification are the basis of quick and effective product/service design. Considering the uncertainty of customer requirements, a customer clustering and pattern identification approach based on vague C-means was proposed. Aiming at the problem that the traditional fuzzy C-means based on Euclidean distance cannot deal with the distance between vague sets, a vague cross-entropy approach was adopted to deal with the distance calculating problem in the C-means clustering algorithm. At the same time, the vague cross-entropy was also applied in calculating the similarity between new customer and different customer groups, and then the customer identification was realized. Finally, a case study of customer clustering and identification in a mechanical company's service development was presented to illustrate the effectiveness of the proposed approach.