USING ANALYTICAL CRM SYSTEM TO REDUCE CHURN IN THE TELECOM SECTOR: A MACHINE LEARNING APPROACH

ABSTRACT Customers are considered to be the most valuable assets of any business, and thus their loyalty is key to profitability as they indulge in repeat purchases and attract their colleagues through word-of-mouth. In competitive markets such as telecommunications, customers have a lot of flexibility due to the variety of service providers available and the introduction of mobile number portability (MNP) thus they can easily switch services and service providers. Customer churn is, therefore, a major problem among telecommunication companies hence their quest to reduce customer churn rate and retain an existing customer. Customer relationship management systems have been used over the years to track patterns within the customer data, but this could be improved notably with the technological advances hitting the universe on a daily basis. We have moved past the age of innovations around steam engines, electricity, computers, mobile, internet to the current technology trends in artificial intelligence and big data. We are at the cusp of a new wave where enterprises have embraced the application of machine learning in streamlining different business processes. Telecom companies have the advantage of mining large customer datasets that can be leveraged on for predictive analysis using data science. This project explores the use of analytical CRM system in reducing customer churn in the telecom industry using machine learning algorithms to predict customer behavior in order to retain them. Its goal is to analyze all relevant customer data and develop focused customer retention programs. This is on the focus that if you could somehow predict in advance which customers are at risk of leaving, you could develop focused customer retention programs to reduce customer churn.