A biclustering-based method for market segmentation using customer pain points. (January 2016)

• Record Type: Journal Article
• Authors: Wang, Binda; Miao, Yunwen; Zhao, Hongya; Jin, Jian; Chen, Yizeng
• Is Part Of: Engineering applications of artificial intelligence. Volume 47(2015:Nov.)
• Page Start: 101
• Page End: 109
• Publication Date: 2016-01
• Subjects: Biclustering -- Customer pain points -- Market segmentation -- BCBimax algorithm; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2015.06.005
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Market segmentation plays a crucial role in product design and development. However, conventional segmentation approaches based on one-way cluster analysis techniques have met two special challenges in practice. First, conventional approaches that derive a global result rather than a local one fail to cluster customers into such groups who have similar characteristics on a fraction of variables. Second, since there is no formal mechanism to select appropriate segmentation variables, different combination of variables will obtain different segmentation results, which makes the approaches not quite convincing. To overcome the two limitations, a novel biclustering-based market segmentation method by using customer pain points is proposed in this paper. Different from one-way algorithms clustering only rows or only columns, biclustering algorithms cluster both rows associated with customers and columns associated with customer pain points simultaneously to identify homogenous subgroups of customers with common characteristics towards a subset of segmentation variables. In addition, customer pain points are used to replace traditional segmentation variables in the presented method, which makes the results more reasonable. Subsequently, an illustrated example is studied to demonstrate the effectiveness of the presented method. Highlights: A novel biclustering-based market segmentation method by using customer pain points is proposed. Biclustering algorithms perform simultaneous clustering of both rows and columns. We employ customer pain points to replace traditional segmentation variables. An illustrated example is studied to demonstrate the effectiveness of the presented method.