Efficient mining for frequent itemsets with multiple convertible constraints

Recent work has highlighted the importance of the constraint-based mining paradigm in the context of frequent itemsets, associations, correlations, and many other interesting patterns in large database. The notion of convertible constraints has been raised in some research. By using the technique some constraints can be pushed into a algorithm for frequent itemsets mining. In this paper, we study multiple convertible constraints and develop technique which enable them to be readily pushed deep inside a algorithm for frequent itemsets mining. By using a sample database we analyze the constraints and then select an optimal method to convert them to convertible constraints for data mining. Results from our detailed experiment show the effectiveness of the algorithm.