Prediction of Customer Churn in Telecom Industries
Shivam Sharm1, Suryavamsi Saripudi2, Sushasukhanya3
1Shivam Sharm, SRM Institute of Science and Technology, Chennai (Tamil Nadu), India.
2Suryavamsi Saripudi, SRM Institute of Science and Technology, Chennai (Tamil Nadu), India.
3Mr. Sushasukhanya, SRM Institute of Science and Technology, Chennai (Tamil Nadu), India.
Manuscript received on 22 May 2019 | Revised Manuscript received on 08 June 2019 | Manuscript Published on 15 June 2019 | PP: 369-372 | Volume-8 Issue-1S2 May 2019 | Retrieval Number: A00860581S219/2019©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: Churn Examination is one of the widespread used study on Subscription Oriented Businesses for analyzing the behavior and activities of customers in order to predict beforehand which customer is likely to exit the service agreement. Built on Machine Learning procedures and algorithms it has become very significant for companies in today’s marketas securing of another client is more costlier than their maintenance. The paper analyses the relevant studies on Customer Churn Analysis in Telecom Business to present overall information to readers about the commonly used data mining means, and performance of the methods. Initially, we present the details about the availability of public datasets and various customer details in each dataset for predicting customer churn. Then, we compare and contrast various analytical modeling systems and compare their performances and results. Conclusively, we review what kinds of performance metrics have been used to gauge the current churn prediction approaches. Examining all these three viewpoints is very critical for developing a more well-organized churn prediction structure.
Keywords: EDA – Exploratory Data Analysis CRM- Customer Relationship Management LRM- Logistic Regression Model SVM-Support Vector Machines.
Scope of the Article: Regression and Prediction