A personalized commodities recommendation procedure and algorithm based on association rule mining

The double-quick growth of EB has caused commodities overload, where our customers are not longer able to efficiently choose the products adapt to them. In order to overcome the situation that both companies and customers are facing, we present a personalized recommendation, although several recommendation systems which may have some disadvantages have been developed. In this paper, we focus on the association rule mining by EFFICIENT algorithm which can simple discovery rapidly the all association rules without any information loss. The EFFICIENT algorithm which comes of the conventional Aprior algorithm integrates the notions of fast algorithm and predigested algorithm to find the interesting association rules in a given transaction data sets. We believe that the procedure should be accepted, and experiment with real-life databases show that the proposed algorithm is efficient one.