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

In many industries, such as the telecommunications industry, identifying the causes of customerchurn is a primary challenge. In the telecommunications industry, it is of great importance to predict whichcustomers will abandon or continue their subscriptions. Machine learning and data science offer numeroussolutions to this problem. These proposed solutions have an important place in decision-making processesin various sectors. This study aims to predict lost customers using machine learning algorithms and explainthe reasons behind them. Linear Regression, Logistic Regression, Naive Bayes, Decision Tree, RandomForest, K-Nearest Neighbors (KNN), Gradient Boosting, XGBoost (eXtreme Gradient Boosting), LightGBM,AdaBoost, and CatBoost were used to find the classification with the best performance on the dataset used. Inthis process, performance metrics such as Accuracy, Precision, Recall, and F1-Score are used to compare theperformance of models. Finally, the LightGBM model, which gave the highest accuracy value (73.085%), wasexplained using explainable artificial intelligence (XAI) algorithms.