Shopping-centre selection modelling: a segmentation approach

This paper highlights the relevance of implementing a segmentation strategy in shopping-centres as their competitive environment becomes more turbulent. We have undertaken empirical research that uses the methodology of consumer choice modelling, as a way to ascertain the determinants of shopping-centre preference, which should form the base of strategy design. We construct a multinomial logit model which uses perceived shopping-centre value dimensions as explanatory variables. We estimate the model, first, for the sample as a whole and, second, by consumer segment, with the objective of comparing model fit and predictive efficiency. The analysis of results shows that estimation at the segment level produces better model fit; moreover, the parameter estimates are different for each group, which indicates that the preference structures and the sensitivity to changes in shopping-centre perceived value vary among segments.