A scalable algorithm for the market basket analysis

The market basket is defined as an itemset bought together by a customer on a single visit to a store. The market basket analysis is a powerful tool for the implementation of cross-selling strategies. Especially in retailing, it is essential to discover large baskets, since it deals with thousands of items. Although some algorithms can find large itemsets, they can be inefficient in terms of computational time. The aim of this paper is to present an algorithm to discover large itemset patterns for the market basket analysis. In this approach, the condensed data are used and is obtained by transforming the market basket problem into a maximum-weighted clique problem. Firstly, the input data set is transformed into a graph-based structure and then the maximum-weighted clique problem is solved using a meta-heuristic approach in order to find the most frequent itemsets. The computational results show large itemset patterns with good scalability properties.