Association Rule Mining: A Multi-objective Genetic Algorithm Approach using Pittsburgh Technique
Sonia Sharma1, Vinay Chopra2
1PG Scholar Ms. Sonia Sharma, M. tech Student, Department of Computer Science, Punjab Technical University DAVIET Jalandhar (Panjab), India.
2Mr. Vinay Chopra, M. tech Student, Department of Computer Science Punjab Technical University DAVIET Jalandhar (Panjab), India.
Manuscript received on 21 September 2013 | Revised Manuscript received on 28 September 2013 | Manuscript published on 30 September 2013 | PP: 121-124 | Volume-2 Issue-4, September 2013 | Retrieval Number: D0810092413/2013©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Association rules [4] usually found out the relationship between different data entities in given data set and moreover it is very much important task of data mining. Basically, association rule mining is a multi-objective problem, instead of a single objective problem. A multi-objective genetic algorithm approach using Pittsburgh technique is introduced in this paper for discovering the interesting association rules with multiple criteria i.e. support, confidence and simplicity and complexity With Genetic Algorithm. In this paper we have discussed the results on various datasets and show effectiveness of the new proposed algorithm.
Keywords: Data Mining, Genetic Algorithm, Optimization, Association Rule, Measure, Apriori, Genetic Operators, Interestingness, Frequent Item-set
Scope of the Article: Data Mining