An Efficient Association Rules Mining Algorithm Based on Coding and Constraints

The mining association rules is an important research field in data mining. The traditional association rule mining methods often generate too many candidate items and have to scan whole database for generating each candidate item. An efficient association rules mining scheme has been proposed in this paper. First, the sub-block coding method is used for the properties. Moreover, the constraints are made for the antecedent and consequent of rules. By using above strategies, the number of candidate items has reduced as well as the scanning size of the database. Therefore, the algorithm greatly improves the operating efficiency. Experimental results demonstrate that the proposed algorithm is more effective than the traditional approach.