Churn prediction is the demanding field today and to stand in the market place or to capture market and for profit maximization churn prediction is very useful. Churn defines the customers switching another company, this is because the market strategy is rapidly changing. Other competitive companies give something new to the customers with low cost. Hence customers change their service provider very fast. Whereas retaining old customers is easy than gaining new customers. Retaining the customers by giving more offers is easy. The goal of this paper is to predict customer churn which will help to retain them. Many organizations feel the data base containing old customer information effectively predicts or generates the outputs. Data mining plays a vital role in churn prediction. Comparative study of the various classification algorithm can be done to give more accurate results.

Churn, weka, decision tree, classification, telecommunication

[1] Thomas Verbraken, Student Member, IEEE, Wouter Verbeke, and Bart Baesens “A Novel Profit Maximizing Metric for Measuring Classification Performance of Customer Churn Prediction Mode ls” MAY 2013, pp 961
[2] Sam Drazin and Matt Montag “Decision Tree Analysis using Weka”
[3] Georges D. Olle Olle and Shuqin Cai “A Hybrid Churn Prediction Model in Mobile Telecommunication Industry” February 2014, PP 55-62
[4] V. Umayaparvathi, K. Iyakutti “Applications of Data Mining Techniques in Telecom Churn Prediction” March 2012, PP Page 1065-1070
[5]Ms Nisha Saini “Churn Prediction in Telecommunication Industry Using Decision Tree” June 2016
[6] Dr. Mamta Madan, Dr. Meenu Dave, Vani Kapoor Nijhawan “Data Mining for Telecom Customer Churn Management” September 2015, pp. 813-817
[7] Vani Kapoor Nijhawan, Mamta Madan, Meenu Dave ” The Analytical Comparison of ID3 and C4.5 using WEKA” June 2017
[8] Kiran Dahiya, Surbhi Bhatia “Customer Churn Analysis in Telecom Industry” 2015 IEEE
[9] Yong Liu, Yongrui Zhuang “Research Model of Churn Prediction Based on Customer Segmentation and
Misclassification Cost in the Context of Big Data” June 2015
[10] Clement Kirui, Li Hong, Wilson Cheruiyot and Hillary Kirui “Predicting Customer Churn in Mobile Telephony Industry Using Probabilistic Classifiers in Data Mining” March 2013
[11] Ammar A.Q. Ahmed, Maheswari “Churn prediction on huge telecom data using hybrid firefly based classification” March 2017
[12] Adnan Anjum, Adnan Zeb, Imran Uddin Afridi, Pir Masoom Shah, Saeeda Usman, “ Optimizing Coverage of Churn Prediction in Telecommunication Industry” 2017
[13] HelenTreasaSebastian* and RupaliWagh “ Churn Analysis in Telecommunication using Logistic Regression” March 16, 2017, Pgs. 207-212
[14] Gaganjot Kaur, Amit Chhabra “Improved J48 Classification Algorithm for the Prediction of Diabetes” Volume 98 – No.22, July 2014
[15] P.Rutravigneshwaran” A Study of Intrusion Detection System using Efficient Data Mining Techniques” IJCSE Journal Vol.5 , Issue.6 , pp.5-8, Dec-2017
[16] U.Kaur 1 , M. Mahajan2 , D. Singh” A Comparative Analysis of Trust Models in Cloud Computing”IJCSE Journal
Vol.6,Issue.2,pp.19-23,Apr-2018