Churn Prediction in Telecommunication Business using CNN and ANN

Main Article Content

Madhuri D. Gabhane, Dr. Aslam Suriya, Dr. S.B. Kishor

Abstract

Customers play a critical part in the operation of the industries. The consumer's tendency to switch brands can have a variety of consequences. Customer churn forecast must be a critical component of every organization's strategy. As a result, clients who are likely to abandon their membership to a service can be identified more easily. Recently, the telecommunications industry has transitioned from a rapidly expanding business to one that has reached saturation. The goal of telecommunications companies is to transition away from the acquisition of new major customers and toward the retention of existing customers. Therefore, it is beneficial to identify which consumers are likely to switch to a competitor's product or service in the foreseeable future. Deep learning technologies such as Artificial Neural Network (ANN) and Convolutional Neural Network (CNN) are used in the development of the model for churn prediction in telecommunication companies. In this research, the dataset is collected from the Kaggle website. The dataset is then pre-processed using several techniques and the necessary features are extracted. Once the relevant features are extracted, they are given to Deep learning algorithms such as ANN and CNN to develop a model. To evaluate feature extraction and classification, several performance metrics are used, such as True Positive Rate (TPR), True Negative Rate (TNR), False Negative Rate (FNR), False Positive Rate (FPR), and precision.

Article Details

Section
Articles