December 2016 Issue Vol.6 No.12
M.Phil Research Scholar,Department of Computer Science,Nandha Arts and Science College, Erode,Tamil Nadu, India
Assistant Professor,Department of Computer Science,Nandha Arts and Science College,Erode,Tamil Nadu, India
Assistant Professor,Department of Computer Science,Nandha Arts and Science College,Erode, Tamil Nadu, India
Abstract: Frequent items are an item that occurs frequently in the dataset. Frequent item set mining (FIM) is a one of the core data mining operation. Frequent item set mining is mainly used for market basket analysis. Consider an example a set of items that contains bread and butter which always occurs frequently together. A traditional frequent item set mining algorithm are Apriori and FPgrowth algorithm. Apriori algorithm is a level-wise iterative approach were k items are used to generate the k+1 items.Apriori algorithm consists of two steps join step and prune step. Initially candidate items are generated by joining process after that by checking the minimum support count frequent items will be generated. The process will be repeated until all k frequent items generation. However, it has a disadvantage that many candidate items should generate which increases the computing time. To overcome that a pattern growth approach algorithm is proposed which significantly reduce the size of candidate sets. FP-Growth algorithm adopts a divide and conquers strategy for finding frequent item sets. It also has some disadvantage that frequent items are generated by repeated scanning of database and recursive traversing of tree.
Keywords:Data Mining, Frequency Item Set, Apriori.