Research Article

Comparative Analysis of XAI Techniques on Telecom Churn Prediction Using SHAP and Interpreted ML Partial Dependence

Volume: 14 Number: 2 June 27, 2025
EN TR

Comparative Analysis of XAI Techniques on Telecom Churn Prediction Using SHAP and Interpreted ML Partial Dependence

Abstract

A comparative analysis of two prominent Explainable Artificial Intelligence (XAI) techniques, SHAP (SHapley Additive exPlanations) and Interpreted ML Partial Dependence, was conducted on a Telecom Churn dataset. The objective of this study was to evaluate and compare the effectiveness of these techniques in enhancing the transparency and interpretability of machine learning models, specifically in telecom churn prediction. The study emphasizes the importance of XAI in ensuring trust and comprehension in predictive modeling. The methodology outlined the steps of data preprocessing and model training. Two separate analyses using SHAP and Interpreted ML Partial Dependence were conducted to evaluate their effectiveness in explaining model decisions and uncovering feature importance. The results of both techniques were discussed, highlighting their strengths and weaknesses, and providing valuable insights into interpretability and robustness. The SHAP analysis demonstrated that it is a powerful tool for identifying which features influence churn, thereby making it easier to understand why the model made certain predictions. The Interpreted ML Partial Dependence method showed the general effects of features, allowing for a broader perspective on model behavior. These results enhanced the transparency of model decisions, instilling trust in users and helping them understand how the model works. The comparative analysis contributed to understanding XAI methods and emphasized the importance of selecting appropriate techniques to enhance transparency in telecom churn prediction models.

Keywords

References

  1. Y. Qi, Jun Wang, Xin Ma, Na Dong, Hong-Mei Yuan, "Coupon Recommendation System Based on Machine Learning and Simulated Annealing Algorithm," Other Conferences, 2023.
  2. Fadhlullah Ramadhani, Reddy Pullanagari, Gabor Kereszturi, Jonathan Procter, "Mapping of Rice Growth Phases and Bare Land Using Landsat-8 OLI with Machine Learning," International Journal of Remote Sensing, 2020.
  3. Yue Qiu, Jianan Fang, "Prediction of Potential Credit Card Users of Bank Based on Deep Learning," Neural Networks, Information and Communication Engineering, 2022.
  4. Félix Lussier, Vincent Thibault, Benjamin Charron, Gregory Q. Wallace, Jean-Francois Masson, "Deep Learning and Artificial Intelligence Methods for Raman and Surface-enhanced Raman Scattering," Trends in Analytical Chemistry, 2020.
  5. V Kirankumar, Somula Ramasubbareddy, G Kannayaram, K Nikhil Kumar, "Classification Of Diabetes Disease Using Support Vector Machine," Journal of Computational and Theoretical Nanoscience, 2019.
  6. Garima Jain, Rajeev Ranjan Prasad, "Machine Learning, Prophet and XGBoost Algorithm: Analysis of Traffic Forecasting in Telecom Networks with Time Series Data," 2020 8th International Conference on Reliability, Infocom ..., 2020.
  7. K. Kikuma, Takeshi Yamada, Koki Sato, K. Ueda, "Preparation Method in Automated Test Case Generation Using Machine Learning," Proceedings of the 10th International Symposium on ..., 2019.
  8. Sandro Skansi, Kristina Sekrst, Marko Kardum, "A Different Approach for Clique and Household Analysis in Synthetic Telecom Data Using Propositional Logic," 2020 43rd International Convention on Information, ..., 2020.

Details

Primary Language

English

Subjects

Robotics

Journal Section

Research Article

Publication Date

June 27, 2025

Submission Date

August 6, 2024

Acceptance Date

March 24, 2025

Published in Issue

Year 2025 Volume: 14 Number: 2

APA
Özkurt, C. (2025). Comparative Analysis of XAI Techniques on Telecom Churn Prediction Using SHAP and Interpreted ML Partial Dependence. Türk Doğa Ve Fen Dergisi, 14(2), 11-25. https://doi.org/10.46810/tdfd.1529139
AMA
1.Özkurt C. Comparative Analysis of XAI Techniques on Telecom Churn Prediction Using SHAP and Interpreted ML Partial Dependence. TJNS. 2025;14(2):11-25. doi:10.46810/tdfd.1529139
Chicago
Özkurt, Cem. 2025. “Comparative Analysis of XAI Techniques on Telecom Churn Prediction Using SHAP and Interpreted ML Partial Dependence”. Türk Doğa Ve Fen Dergisi 14 (2): 11-25. https://doi.org/10.46810/tdfd.1529139.
EndNote
Özkurt C (June 1, 2025) Comparative Analysis of XAI Techniques on Telecom Churn Prediction Using SHAP and Interpreted ML Partial Dependence. Türk Doğa ve Fen Dergisi 14 2 11–25.
IEEE
[1]C. Özkurt, “Comparative Analysis of XAI Techniques on Telecom Churn Prediction Using SHAP and Interpreted ML Partial Dependence”, TJNS, vol. 14, no. 2, pp. 11–25, June 2025, doi: 10.46810/tdfd.1529139.
ISNAD
Özkurt, Cem. “Comparative Analysis of XAI Techniques on Telecom Churn Prediction Using SHAP and Interpreted ML Partial Dependence”. Türk Doğa ve Fen Dergisi 14/2 (June 1, 2025): 11-25. https://doi.org/10.46810/tdfd.1529139.
JAMA
1.Özkurt C. Comparative Analysis of XAI Techniques on Telecom Churn Prediction Using SHAP and Interpreted ML Partial Dependence. TJNS. 2025;14:11–25.
MLA
Özkurt, Cem. “Comparative Analysis of XAI Techniques on Telecom Churn Prediction Using SHAP and Interpreted ML Partial Dependence”. Türk Doğa Ve Fen Dergisi, vol. 14, no. 2, June 2025, pp. 11-25, doi:10.46810/tdfd.1529139.
Vancouver
1.Cem Özkurt. Comparative Analysis of XAI Techniques on Telecom Churn Prediction Using SHAP and Interpreted ML Partial Dependence. TJNS. 2025 Jun. 1;14(2):11-25. doi:10.46810/tdfd.1529139

Cited By

This work is licensed under the Creative Commons Attribution-Non-Commercial-Non-Derivable 4.0 International License.