Efficient mining high utility item sets from transactional databases using up-growth and up-growth+ algorithm

×

Error message

User warning: The following theme is missing from the file system: journalijdr. For information about how to fix this, see the documentation page. in _drupal_trigger_error_with_delayed_logging() (line 1138 of /home2/journalijdr/public_html/includes/bootstrap.inc).

International Journal of Development Research

Efficient mining high utility item sets from transactional databases using up-growth and up-growth+ algorithm

Abstract: 

One of the important research area in data mining is high utility pattern mining. Discovering item sets with high utility like profit from database is known as high utility item set mining. There are number of existing algorithms have been work on this issue. Some of them incurs problem of generating large number of candidate item sets. This leads to degrade the performance of mining in case of execution time and space. In this paper we have focus on UP-Growth and UP-Growth+ algorithm which overcomes this limitation. This technique uses tree based data structure, UP-Tree for generating candidate item sets with two scan of database. In this paper we extend the functionality of these algorithms on transactional database. Discovering item sets with high utility like profitable items from database is known as high utility item set mining. There are many number of existing algorithms have been work on this issue. But some of them incurs problem of generating large number of candidate item sets. This affects to degrade the performance of mining in case of execution time and space. In this paper we have focus on UP-Growth and UP-Growth+ algorithm which will overcome this limitation. This technique uses tree based data structure finding item sets, UP-Tree for generating candidate item sets with two scan of database. In this paper we extend the functionality of UP-Growth and UP-Growth+ algorithms on transactional database. In High utility item sets mining the objective is to identify item sets that have utility value above a given utility threshold to generate tree.

Download PDF: