Identification of churn affecting factors for customer satisfaction in telecommunication industry using Deep Learning

One of the key sectors in developed nations is now telecommunications. Reduce customer turnover, sometimes referred to as customer attrition, as much as possible in order to compete in the very competitive telecommunications sector. It is an essential issue and also the major uncertainties for the huge businesses. So, the organization have plan in generating methods for predicting probable customer churn due to its direct impact over their revenues especially in the telecom sectors. Companies are working to create methods to predict probable customer churn because it has a direct impact on their revenues, particularly in the telecom industry. Since consumers are their primary source of income, businesses in the business sector are seeking for strategies to keep them. The primary contribution of research is the analysis of data on customer behavior, where customer churn is a common occurrence, and the development and validation of a churn prediction model. However, because to its capacity to analyze enormous volumes of consumer data, Deep Learning (DL) is one of the modern techniques employed in churn research. Therefore, the goal of this study is to determine whether the Recency Frequency Monetary (RFM) pattern with the DL methods have been utilized in analyzing the future and existing customer churn in the telecommunication sector.