A Technique for Estimating Updated Frequent Itemsets in ESC-Growth Algorithm

Abstract

In discovering association rules from a dynamic database, iteration through the frequent itemsets requires significant resources and computational time for construction of sub-trees, sub-tree traversal and generation of conditional pattern bases, and it is quite possible that no updated frequent itemsets may have been found at all, resulting in a waste of resources and computational time. We describe a technique for estimating the support count for the itemsets for the next iteration of discovery of the frequent itemsets by our ESC-Growth Algorithm. This technique reduces the need to construct a new sub-tree and next discovery step. If no frequent itemsets in the updated database have been found in the next iteration, ESC-Growth will not construct a new sub-tree and will stop discovering new frequent itemsets in that iteration, reducing the waste of resources and computational time. We measured execution time and sub-tree counts for FP-Growth, FUFP-tree, FPISC-Growth and ESCGrowth on the same synthetic dataset; we found that, at 5% minimum support threshold, ESC-Growth used only 40.3, 96.5, and 99.6% of the execution time required by FP-Growth, FUFPtree and FPISC-Growth, respectively.