An Efficient Approach Using FM-Weight for Revenue Prediction on Rare Itemsets
M. Jeyakarthic1, S. Selvarani2
1M. Jeyakarthic, Department of Computer and Information Sciences, Annamalai University, Annamalai Nagar, Chidambaram (Tamil Nadu), India.
2S. Selvarani, PG, Department of Computer Science, Government Arts College, C-Mutlur, Chidambaram (Tamil Nadu), India.
Manuscript received on 23 April 2019 | Revised Manuscript received on 02 May 2019 | Manuscript Published on 08 May 2019 | PP: 226-232 | Volume-7 Issue-5S3 February 2019 | Retrieval Number: E11430275S19/19©BEIESP
Open Access | Editorial and Publishing 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: A pattern is a social event of exercises that happen together in a database. Past examinations in the field are normally committed to the issue of regular pattern investigation where just precedents that appear as frequently as conceivable in the data are mined. In this manner, structures including exercises that appear in couple of instructive accumulations are not retrieved. We propose a structure to address different orders of intriguing precedents and after that instantiate it to the specific occasion of extraordinary models. Our focus is strived towards rare itemsets mining. The goal of this work is to show that applying additional measures support, confidence and lift framework to disclosure of rare association rules. Moreover, we proposed new algorithm for finding rare itemsets with high revenues from FM-weighted transactions with client analysis. The experimental results outperformed those found utilizing the traditional approach in the prediction of revenue from clients in next-period transactions.
Keywords: Association Rule Mining, Rare Association Rule Mining, RFM Analysis, Weighted Association Rule.
Scope of the Article: Regression and Prediction