Customer Churn Prediction for Imbalanced Class Distribution of Data in Business Sector

Churners are those people who are about to transfer their business to a competitor or simply who cancel a subscription to a service. This paper is based on a specific business sector, which is telecommunication sector. With a churn rate of 30%, the telecommunication sector takes the first place on the list. In this paper, we present some advanced data mining methodologies which predicts customer churn in the pre-paid mobile telecommunications industry using a call detail records dataset. To implement the predictive models, we initially propose and then apply four machine learning algorithms: Random Forest, Naïve Bayes, Logistic Regression, and XG Boost. To evaluate the models, we use various evaluation metrics and find the best model which will be suitable for any class imbalanced data and also our business case. This paper can also be viewed as a comparative study on the most popular machine learning methods applied to the challenging problem of customer churn prediction.

Download Full-text

Customer Churn Prediction in Telecommunication Industry Using Data Certainty

International Journal of Scientific Research in Science Engineering and Technology ◽

10.32628/ijsrset207142 ◽

2020 ◽

pp. 252-258

Author(s):

V R Reji Raj ◽

Rasheed Ahammed Azad .V

Keyword(s):

Machine Learning ◽

Market Value ◽

Machine Learning Algorithms ◽

Telecommunication Industry ◽

Churn Prediction ◽

Customer Churn ◽

The Past ◽

Customer Churn Prediction ◽

Using Data ◽

Data Certainty

Customer churn is a major problem affecting large companies, especially in telecommunication field. So the telecom industries have to take the necessary steps to retain their customers, to maintain their market value. So companies are seeking to develop methods that predict potential churned customers. We have to find out the factors that increase customer churn for making necessary actions to reduce churn. In the past, different data mining techniques have been used for predicting the churners. Here the most popular machine learning algorithms used for churn predicting are analysed. The conclusions are stated with the help of suitable tables.

Download Full-text

Multi-objective rain optimization algorithm with WELM model for customer churn prediction in telecommunication sector

Complex & Intelligent Systems ◽

10.1007/s40747-021-00353-6 ◽

2021 ◽

Author(s):

Irina V. Pustokhina ◽

Denis A. Pustokhin ◽

Phong Thanh Nguyen ◽

Mohamed Elhoseny ◽

K. Shankar

Keyword(s):

Machine Learning ◽

Optimization Algorithm ◽

Service Providers ◽

Sampling Rate ◽

Optimal Sampling ◽

Churn Prediction ◽

Telecommunication Sector ◽

Multi Objective ◽

Customer Churn ◽

Customer Churn Prediction

AbstractCustomer retention is a major challenge in several business sectors and diverse companies identify the customer churn prediction (CCP) as an important process for retaining the customers. CCP in the telecommunication sector has become an essential need owing to a rise in the number of the telecommunication service providers. Recently, machine learning (ML) and deep learning (DL) models have begun to develop effective CCP model. This paper presents a new improved synthetic minority over-sampling technique (SMOTE) with optimal weighted extreme machine learning (OWELM) called the ISMOTE-OWELM model for CCP. The presented model comprises preprocessing, balancing the unbalanced dataset, and classification. The multi-objective rain optimization algorithm (MOROA) is used for two purposes: determining the optimal sampling rate of SMOTE and parameter tuning of WELM. Initially, the customer data involve data normalization and class labeling. Then, the ISMOTE is employed to handle the imbalanced dataset where the rain optimization algorithm (ROA) is applied to determine the optimal sampling rate. At last, the WELM model is applied to determine the class labels of the applied data. Extensive experimentation is carried out to ensure the ISMOTE-OWELM model against the CCP Telecommunication dataset. The simulation outcome portrayed that the ISMOTE-OWELM model is superior to other models with the accuracy of 0.94, 0.92, 0.909 on the applied dataset I, II, and III, respectively.

Download Full-text