Datamining Application in Retailing

Abstract

Retail is identified as a sector that is poised to show highest growth in the coming years. The sector is set for a revolution by both present players & new entrants to explore the market. It is expected to grow by 25 – 30% by 2010. As, business has gone more customer – centric, this paper investigates Market Basket Analysis as an important component of analytical CRM in retail organizations. Selling as many different products  as possible to customers maximizes the value to business. Market Basket Analysis (MBA) applies association of rules learning to purchase data with the goal of identifying cross selling opportunities. Given a data set, the algorithm trains and identifies product baskets and product association rules. Product baskets (referred to as item sets) are groups of products purchased together at checkout. Product association rules predict the  purchase of one or more other products (the consequent) given the known presence of some products in a basket (the antecedent).So Market Basket Analysis (MBA) is used as a technique to make retailers understand what combinations of product items, customer may tend to purchase at the same time or later on as a follow-up purchase and thereby giving an idea to retailers which product items sell together. Therefore, this paper has focused on how MBA seeks to find relationship between purchases in a departmental store in Trichy region by formation of rules like IF {Detergent powder, No Detergent bar} THEN {Brush}, for the purchase items taken into analysis. This technique acts as an excellent cross-selling promotional measure in retail segment.