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

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.