, and

Abstract. Market basket analysis techniques are substantially important to everyday’s business decision, because of its capability of extracting customer’s purchase rules by discovering what items they are buying frequently and together. But, the traditional single processor and main memory based computing is not capable of handling ever increasing large transactional data. Moreover, due to the presence of null transactions mining performance degrades drastically in existing approaches. Therefore, in this paper an attempt has been taken to remove these limitations. First we remove null transactions and infrequent items from the segmented dataset prior applying our proposed HMBA algorithm using the ‘ComMapReduce ’ framework on Hadoop to generate the complete set of maximal frequent itemsets; since, the maximal frequent itemsets for a particular customer reveals his/her purchase rules. Later on, modified version of the ‘sequence close level ’ is used for counting the distance between a pair of items for mining customer’s purchase rules. Experimental results show that our market basket analysis technique is not only increases the performance, but also highly scalable in terms of increasing loads, and can analyze the customer’s purchase rules in a reasonable time