International Journal of Computer Science Issues

More than a traditional journal...

Acquisition and the retention of customers are the top most concerns in todays business world. The rapid increase of the market in every business is leading to higher subscriber base for service providers. In such situation, companies have realized the importance of retaining the on hand customers. It is therefore mandatory for the service providers to reduce churn rate because the negligence could be resulted as profitability reduction in major perspective. Churn prediction helps in identifying those customers who are likely to leave a company. Among all other segments, telecommunication is coping with the highest churn rate. Certain data mining techniques enable these telecommunication companies to be equipped with effective methods for examining their clients behavior and on the basis of this analysis, possible future departures could be targeted. The paper reviews 61 articles to survey the pros and cons of renowned data mining techniques used to build predictive customer churn models specifically in the field of telecom. Findings of this paper reveal the fact that a very less amount of work has been done in the field of land line telephony as compare to wireless telephony. On the other hand, Decision Tree has been emerged as the most likely used prediction model for predicting telecom customer churn. Thus the paper provides a roadmap to researchers for knowledge accumulation about data mining techniques in the field of telecommunication.