CUSTOMER CHURN PREDICTION IN TELECOMMUNICATIONS INDUSTRY USING MACHINE LEARNING

Abstract

In this study, we looked at both the definition of customer turnover and methods for predicting it. In order to learn more about predicting customer turnover, we looked at a variety of academic papers. Seven machine learning algorithms were also trained using data from kaggle.com. To establish which algorithm performs better in terms of likelihood to forecast customer turnover, we used a confusion matrix, recall score, precision score, f1 score, accuracy score and classification report. The outcome demonstrates that Random Forest and Support Vector Machine have the highest probabilities to forecast customer, respectively.

Identifiers

Resource ID

urn:uuid:a55e08ff-f78b-4975-a2b6-040497a7029f