Prediction of Customer Churn in Telecom Sector using Clustering Technique
Vallabhaneni Renuka Devi1, G. Bharathi2, G.V.S.N.R.V. Prasad3
1Vallabhaneni Renuka Devi, M.Tech Student, Department of CSE, Gudlavalleru Engineering College, Gudlavalleru, (A.P), India.
2Mrs. G. Bharathi, Professor, Department of CSE, Gudlavalleru Engineering College, Gudlavalleru, (A.P), India.
3Dr. G.V.S.N.R.V. Prasad, Professor and Vice Principal Academics, Department of CSE, Gudlavalleru Engineering College, Gudlavalleru, (A.P), India.
Manuscript received on 15 September 2019 | Revised Manuscript received on 24 September 2019 | Manuscript Published on 10 October 2019 | PP: 826-832 | Volume-8 Issue-6S2, August 2019 | Retrieval Number: F12070886S219/19©BEIESP | DOI: 10.35940/ijeat.F1207.0886S219
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: These days the data is producing at an incredible rate. Handling and analyzing such a big data in a specific time is the main challenge today. Clustering is majorly familiar with analyzing the data visually and used for efficient decision making process. Clustering is broadly used in a range of applications like education, field of computer science, marketing, insurance, surveillance detection, fraud detection and scientific discovery to mine the functional information from the data. This paper concentrates on the unsupervised learning k-means clustering algorithm to perform the analysis on churn prediction on telecom sector. The selection of distance measures and the category of data that a clustering algorithm cans effort is a decisive step in clustering. It defines how two elements are resemblance with each other and how this resemblance will impact the outline of the clusters. Another foremost difficulty in clustering process is to determine the goodness or validity of the cluster. Hence this paper discusses and addresses the different issues with K-means clustering. Experimentation was done on china telecom data to identify analogous group of clients who more likely to prone from the services is a major task. The results were analyzed to identify best feature, distance measures and validity indices to get qualitative clusters.
Keywords: Clustering, Unsupervised Learning, K-Means, Validity Indexes.
Scope of the Article: Clustering