ABSTRACT: This study presents a comparative analysis of Support Vector Machine (SVM) and Random Forest models for predicting customer churn in the telecom industry, with a focus on enhancing these models through the integration of fuzzy logic. Customer churn is a critical issue for telecom companies, and accurately predicting churn can significantly impact customer retention strategies. The research explores the effectiveness of SVM and Random Forest, two widely used machine learning algorithms, in churn prediction. Fuzzy logic is incorporated into both models to address the inherent uncertainties and complexities in customer behavior, allowing for more nuanced and accurate predictions. Experimental results demonstrate that the integration of fuzzy logic improves the performance of both models, with the fuzzy-enhanced Random Forest model achieving the highest accuracy, precision, recall, and F1-score. These findings highlight the potential of combining machine learning with fuzzy logic to develop more robust predictive models in the telecom sector.