A Frequent Item Graph Approach for Discovering Frequent Itemsets

Efficient algorithms to discover frequent patterns are crucial in data mining research. Finding frequent item sets is computationally the most expensive step in association rule discovery and therefore it has attracted significant research attention. In this paper, we present a more efficient approach for mining complete sets of frequent item sets. It is a modification of FP-tree. The contribution of this approach is to count the frequent 2-item sets and to form a graphical structure which extracts all possible frequent item sets in the database. We present performance comparisons for our algorithm against FP-growth algorithm.