The model of multiple correspondence analysis for customer segmentation in large retail groups

Abstract

The objective of the present work is to highlight the importance of multidimensional categorical models applied to marketing strategies, with particular regard to customer segmentation. On the basis of an extensive investigation ,we seek to determine the motivations that encourage the interviewed subjects to choose the Mongolfiera Ipercoop hypermarkets of the Apulia region, to identify how much they spend there, and to analyse the characteristics of the products they consider for purchase.

In order to attain these objectives, we have employed multiple correspondence analysis which, by means of maps constructed on a limited number of latent variables, simplifies the reading of the intricate relations among the numerous categorical variables observed and their modalities. In market research on the purchasing behavior of consumers, these analyses are used to determine the essential aspects of that behavior as a rational basis for the choice of opportune marketing strategies.