Skip navigation
Please use this identifier to cite or link to this item: http://repository.iitr.ac.in/handle/123456789/18233
Title: Analysis of Clustering and Classification Methods for Actionable Knowledge
Authors: Arumugam, Paramasivan
Christy V.
Published in: Proceedings of Materials Today
Abstract: Data Mining becomes a vital aspect in data analysis. Study on data mining is very much depends on the performance of the clustering. Clustering before classification is termed as cluster Classifier. Recently knowledge based approached has become the key forces in data classification. Here performed a four way comparison of Logistic Regression (LR), Classification and Regression Trees (CART), Random Forest (RF) and Neural Network (NN) models using a continuous and categorical dependent variable for classification. A Customer relationship management (CRM) data set is used to run these models. Measurement of different classification accuracy methods are used to compare the performance of the models. Based on the efficient method actionable knowledge is derived from the proposed methodology. © 2017 Elsevier Ltd.
Citation: Proceedings of Materials Today, (2018), 1839- 1845
URI: https://doi.org/10.1016/j.matpr.2017.11.283
http://repository.iitr.ac.in/handle/123456789/18233
Issue Date: 2018
Publisher: Elsevier Ltd
Keywords: Actionable Knowledge
Classification
Clustering
Data Mining
Random Forest
ISSN: 22147853
Author Scopus IDs: 16068034900
57200451156
Author Affiliations: Arumugam, P., Department of Statistics, Manonmanium Sundar University, Tirunelveli, Tamilnadu, India
Christy, V., Department of Statistics, Manonmanium Sundar University, Tirunelveli, Tamilnadu, India
Corresponding Author: Christy, V.; Department of Statistics, Manonmanium Sundar UniversityIndia; email: christy.eben@gmail.com
Appears in Collections:Conference Publications [PH]

Files in This Item:
There are no files associated with this item.
Show full item record


Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.