Abstract

In the face of extreme competitive telecommunication market, the cost of acquiring new customer is much more expensive than to retain the existing customer. Therefore, it has become imperative to pay much attention towards retaining the existing customers in order to get stabilize in market comprised of vibrant service providers. In current market, a number of prevailing statistical techniques for customer churn management are replaced by more machine learning and predictive analysis techniques. This article reviews the customer churn prediction problem, factors escalating the phenomena, prediction through predictive analytics, steps for processing of predictive analytics and evaluation of performance metrics for various churn prediction models are surveyed. Moreover, the CRM data from Pakistan Telecommunication Company limited as case study to discuss the process of data mining and predictive analytics for customer churn prediction.

Highlights

  • THE public services has improved significantly on the emergence of mobile phone technology and delivered benefits to common citizen in term of connectivity, access to markets and social integration

  • In today competitive world of telecommunication technology, the surviving of operators is quite difficult due to frequent movement of customers who are discarding a particular service on basis of dissatisfaction or acquiring of offering from another service provider

  • This phenomena is termed as churn that has help customer obtained better service on one hand but lead significant revenue or profit loss to that network providers invested in one of expensive market

Read more

Summary

INTRODUCTION

THE public services has improved significantly on the emergence of mobile phone technology and delivered benefits to common citizen in term of connectivity, access to markets and social integration. In today competitive world of telecommunication technology, the surviving of operators is quite difficult due to frequent movement of customers who are discarding a particular service on basis of dissatisfaction or acquiring of offering from another service provider. This phenomena is termed as churn that has help customer obtained better service on one hand but lead significant revenue or profit loss to that network providers invested in one of expensive market. This is imperative to highlight that profit varies according to technique used for predictive analysis which is clearly evident from one of study conducted on 10% customers of company out of total 5 million customer are passed through retention campaign which profit has climbed to hundred thousand dollars by changing the prediction technique [6]

LITERATURE REVIEW
PREDICTIVE ANALYTICS OVERVIEW
Support Vector Machine
Logistic Regression
Discriminant Analysis
Neural Network
CHURN PREDICTION USING PREDICTIVE ANALYSIS MODELING
Recall
PROPOSITION OF MODEL FOR CHURN PREDICTION
Results
VIII. CONCLUSION
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call