<p>This study investigates the combination of numerical modelling and machine learning techniques to evaluate slope stability and predict landslide susceptibility. Slope characteristics, such as slope angle, nail length, and nail inclination, were simulated to generate a dataset representing various stability conditions. Three machine learning algorithms including Logistic Regression, Support Vector Machine, and Naïve Bayes Classifier, were applied to classify slopes and assess their stability. Model performance was evaluated using standard metrics such as accuracy, precision, recall, F1-score, and the Factor of Safety. Results show that Logistic Regression achieved the highest prediction accuracy at 97% and successfully identified all stable slopes, while Support Vector Machine reached 94% accuracy and Naïve Bayes 84% even after optimization. The study also assessed the impact of model optimization on prediction accuracy and emphasized the role of parameter tuning. The findings suggest that machine learning (Logistic Regression) can serve as an effective and practical tool for slope stability assessment.</p>