Machine Learning Approaches for Customer Churn Prediction: Balancing Accuracy and Interpretability
Enregistré dans:
| Publié dans: | ProQuest Dissertations and Theses (2025) |
|---|---|
| Auteur principal: | |
| Publié: |
ProQuest Dissertations & Theses
|
| Sujets: | |
| Accès en ligne: | Citation/Abstract Full Text - PDF |
| Tags: |
Pas de tags, Soyez le premier à ajouter un tag!
|
| Résumé: | The study addresses the problem of customer churn in the telecommunications industry, where retaining existing users is significantly more cost-effective than acquiring new ones. It investigates the application of machine learning techniques for churn prediction using demographic, contractual, service, and billing information. A range of models are evaluated, from interpretable approaches such as Logistic Regression and Decision Trees to advanced methods including Random Forest, Gradient Boosting, Support Vector Machines, and Neural Networks. The analysis emphasizes predictive performance and interpretability, identifies key factors driving churn, and discusses trade-offs among different approaches. The findings provide both methodological insights into the use of machine learning for churn prediction and practical guidance for developing data-driven strategies to improve customer retention. |
|---|---|
| ISBN: | 9798293838837 |
| Source: | ProQuest Dissertations & Theses Global |