English

Abstract

Now a days high utility item sets specially from large transaction databases is required task to process many day to day operations in quick time. In many relevant algorithms presented those are surface the problem of generating large number of candidate item set and thus degrades the mining performance in terms of execution time and space. In this paper mainly three algorithms are presented, such as UP-Growth (utility pattern) for mining high utility item set for pruning candidate item sets. In these algorithms, compact tree structure (UP-Tree) is used for discovering the useful item-set so that candidate item is generated with only two scan of database. The performance of UP-Growth was evaluated in comparison with the state-of-theart algorithms on different types of datasets. We have used this approach with existing UP-Growth and UP-Growth+ with aim of improving their performances further. The experimental results show that UP-Growth not only reduces the number of candidates effectively but also outperforms other algorithms substantially in terms of execution time, especially when the database contains lots of long transactions. If we did not use one of the above algorithm then we will face number of problems like if we are retrieve items then that operation takes more time to scan database. It is a time consuming process. This process reduces performance of the project. So we are prefer other alternatives like using UP growth algorithm, FP growth algorithm etc. In these algorithms also have some drawbacks like time consuming i.e. scans database for multiple times. So all aspects we considered and proposed one algorithm in this project i.e. UP Growth algorithm. It is very efficient algorithm for mining high utility compare to FP growth algorithm and etc.