Predicting Churn In E-Mall Using Decision Tree
Journal Title: International Journal for Research in Applied Science and Engineering Technology (IJRASET) - Year 2017, Vol 5, Issue 6
Abstract
Different studies and reviews propose that for an organization, economically it is less feasible to connect with another new customer than to hold a current faithful customer. Churn foreseen models are produced by scholastics and professionals to successfully oversee and control customer churning with the aim of holding existing customers. As churn management is an important task for organizations to hold faithful clients, the ability to accurately predict customer churn is important. The present paper proposes a clustering based method to deal with prediction of product churning. In the study to anticipate churning, decision tree has been used to predict churning probability. Comparison has been made out between two Decision Tree algorithms namely C5.0 and Rpart and apart from that Svm, Kernel Svm and Naïve Bayes have also been applied on the dataset. On the basis of performance analysis, conclusion has been made c5.0 suits best in case of having imbalanced Data. Sample dataset provided by Amazon, had been used for the current research work.
Authors and Affiliations
Davinder Paul Singh, Vinod Sharma
Keywords
Related Articles
- EP ID EP24432
- DOI -
- Views 315
- Downloads 10
slugHeat Loss Reduction in Submerged Electric Furnace Using Finite Element Analysis for Efficiency Improvement
Now a day energy saving is the main challenged among human beings. Compare to other type of energy Electric energy and Heat energy are the most important energy comes in front everywhere in surroundi...
The Future Scope of Business Intelligence (BI)
Business intelligence (BI) is a broad category of application on programs and technologies for gathering, storing, analyzing, and providing access to data to help enterprise users make better business decisions. BI appl...
Experimental Investigation on Use of Copper Slag and Recycled Aggregate as a Fine Aggregate in Concrete
Conservation of natural resources and preservation of environment is the essence of any modern development. In last few decades, construction activities increase rapidly. Itsss require more raw materials and it will res...
Optimization of Association Rule Mining using FP_Growth Algorithm with GA
Frequent pattern mining is one of the active research themes in data mining which covers a broad spectrum of data mining tasks viz. Association rules, correlations, causality, ratio rules, emerging patterns etc. In this...
Effect of Oxygen Enrichment on Emission Characteristics of a Variable Compression Ratio Diesel Engine
The objective of this research is to explore the effect of oxygen enrichment on emission characteristics for a single cylinder variable compression ratio diesel engine. In this study, a computerised test rig with data a...