Graph Based Approach for Finding Frequent Itemsets to Discover Association Rules

The discovery of association rules is an important task in data mining and knowledge discovery. Several algorithms have been developed for finding frequent itemsets and mining comprehensive association rules from the databases. The efficiency of these algorithms is a major issue since a long time and has captured the interest of a large community of researchers. This paper presents a new approach that can mine frequent itemset or patterns in less time and in a straight forward way. Majority of the algorithms developed for finding frequent itemsets scan the database repeatedly and are based on the concept of minimum threshold support value. The proposed approach is based on graph and finds frequent itemsets without repeatedly scanning the database. The algorithm finds frequent itemsets irrespective of support level and can be used for finding the largest most frequent itemset. The proposed approach performs single scan of the database in first phase and draws a graph in which edges are labeled with the respective transactions ids. In second phase, a table is constructed which has all distinct labels and the corresponding itemsets. The largest most frequent itemset is selected from this table according to the given selection criterion.