Principal Component Analysis based Feature Selection Driving Store Choice: A Data Mining Approach

Abstract

Store choice is a function of store image which in turn comprises of store attributes. Different store attributes are evaluated differently by shoppers. For researchers and managers, it is not easy to understand how shoppers assess the multiple attributes that a store has. The high number of attributes needs to be reduced to a more manageable number and this can be done using the data mining technique of feature selection or factor analysis. Once this data mining technique is applied, the emerging factors can be processed to understand shoppers store choice criteria much better. This study assesses 23 store attributes evaluated by 197 shoppers of hypermarkets in India which were reduced to seven factors. The seven factors were ranked. Price / Value related factor was ranked highest.