International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 27 - Number 5 |
Year of Publication: 2011 |
Authors: CH.M.H.Saibaba, Dr. Rekha Redamalla |
10.5120/3296-4502 |
CH.M.H.Saibaba, Dr. Rekha Redamalla . Mining Frequent Itemsets by using Binary Search Tree Approach. International Journal of Computer Applications. 27, 5 ( August 2011), 27-30. DOI=10.5120/3296-4502
Data Mining is the process of extracting hidden patterns from data. Finding frequent itemsets is computationally the most expensive step in association rule discovery. The Efficient Hashing Tree (EHT) algorithm is even faster than Apriori and FP- growth algorithms. Its drawback is however, that the time needed to build a compact tree and the memory requirement depends upon the number of frequent 2 – itemsets. [1] The above drawbacks are rectified by using Binary Search Tree (BST) algorithm. By using this approach we can construct a binary search tree very quickly by considering the frequent itemsets. This algorithms works well for 1–itemset, 2–itemsets, 3–itemsets and more than 3–itemsets. By using this approach it requires very less memory requirement for mining frequent itemsets.