Angale, Pooja Narendra (2024) Optimizing Customer Churn Prediction in Telecom using Machine Learning: A Comparative Study of Sampling Techniques. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
Customer churn is one of the most prominent challenges to revenue for any telecommunication company. Precise prediction of customer churn is therefore very critical, but class imbalance in the dataset, with very few customers leaving compared to the large number of those remaining loyal, definitely puts it at risk. Standard machine learning models usually perform poorly on the minority class due to this class imbalance. This paper presents solutions to this problem by examining advanced sampling techniques: MSMOTE, MWMOTE, and IMWMOTE. This is a process where the minority samples will be sorted and borderline and noisy cases are handled with extra care. In this paper, comparative analysis is performed to prove that, against baseline models, these advanced sampling techniques significantly improve performance in churn prediction tasks, offering different advantages conditioned on dataset complexity. Applying these methods will make it easy for a telecommunication company to improve its accuracy in predicting the churning customers for better retention efforts.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Kelly, John UNSPECIFIED |
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HF Commerce > Marketing > Consumer Behaviour Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Telecommunications Industry |
Divisions: | School of Computing > Master of Science in Data Analytics |
Depositing User: | Ciara O'Brien |
Date Deposited: | 07 Aug 2025 08:37 |
Last Modified: | 07 Aug 2025 08:37 |
URI: | https://norma.ncirl.ie/id/eprint/8454 |
Actions (login required)
![]() |
View Item |