Customer Churn Prediction: An Empirical Research of Telecommunications Service Provider in the United States

Yifei Dou

2023

Abstract

In the competitive landscape of subscription-based industries, like telecommunications services, customer retention is vital for sustained growth. The dynamic nature of Telecom Industry requires a proactive approach to address customer churn, which can lead to financial losses and damage to reputation. This research uses linear regression analysis to predict customer churn within U.S. telecommunications service providers. By exploring the relationships between customer attributes and churn scores, the study aims to provide actionable insights for informed decision-making. The methodology involves data collection, hypothesis formulation, correlation, and constructing a linear regression model. Through meticulous analysis, the study’s findings reveal that longer subscription tenure and extended contracts are associated with lower churn scores, emphasizing their role in fostering loyalty. Conversely, certain internet service types and higher monthly charges are linked to elevated churn scores, underscoring the importance of service quality and pricing considerations. The research contributes to the strategic arsenal of telecommunications providers, equipping them with a predictive tool to address customer churn and cultivate loyalty.

Paper Citation

in Harvard Style

Dou Y. (2023). Customer Churn Prediction: An Empirical Research of Telecommunications Service Provider in the United States. In Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML; ISBN 978-989-758-705-4, SciTePress, pages 509-514. DOI: 10.5220/0012802000003885

in Bibtex Style

@conference{daml23,
author={Yifei Dou},
title={Customer Churn Prediction: An Empirical Research of Telecommunications Service Provider in the United States},
booktitle={Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2023},
pages={509-514},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012802000003885},
isbn={978-989-758-705-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML
TI - Customer Churn Prediction: An Empirical Research of Telecommunications Service Provider in the United States
SN - 978-989-758-705-4
AU - Dou Y.
PY - 2023
SP - 509
EP - 514
DO - 10.5220/0012802000003885
PB - SciTePress