AN ENHANCED UPGROWTH ALGORITHM FOR TEMPORAL HIGH UTILITY ITEM MINING

High utility item set mining from a transactional database helps to discover the items with high utility based on profit, cost and quantity. Even though many numbers of significant algorithms have been proposed in recent years they experienced the problem of producing a large number of candidate itemsets for high utility itemsets. Such a huge number of candidate item sets degrades and reduces the mining performance in terms of storage space requirement and execution time. The situation may become worse when the database contains lots of datasets, long transactions or long high utility itemsets. The proposal introduces two algorithms which are temporal utility pattern growth (TUP-Growth) and temporal UP-Growth+, for mining high utility itemsets with a set of effective strategies for pruning candidate item sets rapidly. The information of high utility itemsets is maintained in a tree-based data structure named utility pattern tree (TUP-Tree) such that candidate itemsets can be generated efficiently with only two scans of database, then that will be segmented into multiple clusters for fast computation. The proposed algorithms reduce the number of candidates and database scans effectively. This also outperforms best than the existing algorithms and significantly reduces the runtime and memory and storage overhead, especially when databases contain lots of high and long transactions.