A Bibliometric Analysis of Customer Churn Prediction in the Telecommunications Industry

Abstract

Analyzing and exploring vast amounts of scientific data is expected in bibliometric analysis. Statistical and graphical categorized tests are conducted to highlight the spatiotemporal elements of the paper's data and summarize it. Bibliometric analysis helps determine the most influential authors, organizations, and publications in a particular subject. It may also monitor how research trends change over time. This study involved the bibliometric evaluation of papers on customer churn prediction using machine learning (ML) in the Scopus databases. The study used the analytic tools VosViewer and R-Bibliometrics (an open-source R's package for bibliometric analysis powered by the R programming language). Researchers often use a combination of VOS viewer and R-Bibliometrics to harness the strengths of both tools. VOS viewer excels in generating intuitive network visualizations, aiding in identifying research communities and thematic clusters. R-Bibliometrics offers unparalleled flexibility and customization, enabling in-depth statistical analyses and reproducibility in research workflows. Integrating these tools provides a comprehensive approach, leveraging the user-friendly visualization capabilities of VOS viewer analytic features.

Keywords: Big Data, Customer Churn, Performance Analytics, Telecommunications Industry.