Open AccessLiterature Review of Using DWHBI Approaches to Predict and Reduce Customer Churn in Telecommunications Industry
Author(s) -
K. Prakash Krishnan,
A. Kumar Kombaiya
Publication year - 2020
Publication title -
international journal of scientific research in computer science, engineering and information technology
Language(s) - English
Resource type - Journals
ISSN - 2456-3307
DOI - 10.32628/cseit206535
Subject(s) - enhanced telecom operations map , competitor analysis , telecommunications , service provider , telecom infrastructure sharing , business , customer retention , competition (biology) , asset (computer security) , telecommunications service , service (business) , computer science , marketing , service quality , computer security , ecology , biology
In recent days, telecom industry plays a vital role in our daily life. During corona period entire world depends on the telecom services domain. But telecome industry has been facing many surivival problems in the global market since last 10 years due to heavy competition between competitors. To stand in this field, service providers have to understand the complete customer requirements and provide the efficient services to stop the customer movement from one network to another network. Customer churn is one of the most critical problem faced by the telecom industry. In this industry, it is more expensive to bring the new customers as compared to retain the existing customers. The objective of customer churn prediction is to find the subscribers that are ready to move from the current service provider in advance. Churn prediction allows the service providers to offer new benefits and campaign offers to retain the existing customer in the same network. Technically this term would be call it as ‘Win back Situation’ in telecom industry. The high volume of data generated by telecom industry , with the help of data warehosuing and business intelligence implementation would become the main asset for predicting the customer churn. To prevent the churn many models and methods are used by researchers. In this paper, we reviewed different mining methods and the most popular algorithms which used in telecom industry. But this model is not only for telecom domain, it can be implement for other domains which has highly depends on customer interactions.