High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Efficient Data Mining Utility Patterns Without Candidate Generation

Author(s):

Mr. Sanadi Rajesh A , Shriram Institute of Engineering & Technology Center, Paniv, Maharashtra, India; Prof. Dhainje P. B., Shriram Institute of Engineering & Technology Center, Paniv, Maharashtra, India

Keywords:

Data Mining, Utility Mining, High Utility Patterns, Frequent Patterns, Pattern Mining, Association, Clustering, Data Mining Application, Knowledge Discovery Database

Abstract

This paper proposes an algorithm which finds high utility patterns in a single phase without generating candidates. The novelties lie in a high utility pattern growth approach; it’s a look ahead strategy, and a linear data structure. Our pattern growth approach is to search a reverse set enumeration tree and to prune search space by utility upper bounding. We look ahead to identify high utility patterns without enumeration by a closure property and a singleton property. Our linear data structure enables us to compute a tight bound for powerful pruning and to directly identify high utility patterns in an efficient and scalable way that targets the root cause with prior algorithms.

Other Details

Paper ID: IJSRDV5I80194
Published in: Volume : 5, Issue : 8
Publication Date: 01/11/2017
Page(s): 131-133

Article Preview

Download Article