Research methods on telecom user churn

Zhujia Li

doi:10.1117/12.2692470

23 August 2023 Research methods on telecom user churn

Zhujia Li

Proceedings Volume 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023); 1278431 (2023) https://doi.org/10.1117/12.2692470
Event: 2023 2nd International Conference on Applied Statistics, Computational Mathematics and Software Engineering (ASCMSE 2023), 2023, Kaifeng, China

Abstract

The prediction of telecom customer churn is of great significance for the telecommunications industry, and effective and accurate predictions can make countermeasures for the status of customer churn. In order to make more effective predictions, we aim to investigate the most suitable machine learning-based algorithm for the task. In this article, a dataset of telecom customer churn was selected, which includes over 1000 sets of data and involves a comprehensive range of influencing factors. In order to find the algorithm with the best prediction performance, this paper implements various algorithms, such as XGBoost, random forest, decision tree and Adaboost, to analyze and process the data set. By comparing several statistical metrics, it is finally found that XGBoost is the most suitable algorithm for processing this data set, and random forest is not a good choice to process the data set.

Citation Download Citation

Zhujia Li "Research methods on telecom user churn", Proc. SPIE 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023), 1278431 (23 August 2023); https://doi.org/10.1117/12.2692470

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available