Transparency in Decision-Making: The Role of Explainable AI (XAI) in Customer Churn Analysis

Abstract

Abstract In many industries, as in the telecommunications sector, identifying the reasons for customer loss is a primary challenge. Predicting which customers will churn or continue their subscriptions is of utmost importance in the telecommunications sector. Machine learning and data science offer numerous solutions to this issue. These proposed solutions hold a significant place in decision-making processes across various sectors. This study aims to predict lost customers and explain the reasons behind it using machine learning algorithms. The dataset used includes Linear Regression, Logistic Regression, Naive Bayes, Decision Tree, Random Forest, K-Nearest Neighbors (KNN), Gradient Boosting, XGBoost (eXtreme Gradient Boosting), LightGBM, AdaBoost and CatBoost algorithms to find the best-performing classification model. Performance metrics such as $R^2$ score, Mean Squared Error, Mean Absolute Error, Root Mean Squared Error, and Accuracy are used in this process. Finally, the best prediction model is explained using eXplainable Artificial Intelligence (XAI).

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 7 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.