Falls are a major safety concern, especially for older adults, and there is a continued need for reliable and efficient automatic fall detection systems. This paper presents a fall detection approach based on machine learning classifiers trained on numerical features extracted from the UR Fall Detection Dataset (URFD). Instead of operating directly on image or video data, the system uses eight compact geometric and motion-related features, including height-width ratio, major-minor ratio, bounding box occupancy, maximum standard deviation, and related descriptors. Four classification models are evaluated: Random Forest, Support Vector Machine (SVM), XGBoost, and LightGBM. All features are standardized using Standard Scaler prior to training. On a dataset of 11,542 samples, the best-performing model, tuned LightGBM, achieves an accuracy of 96.9%. The untuned LightGBM model reaches 96.4% accuracy, followed by XGBoost (95.6%), Random Forest (95.3%), and SVM (85.6%). The models are assessed using accuracy, precision, recall, and F1-score on a held-out test set of 2,309 samples. The results show that a feature-level representation combined with gradient boosting methods can provide competitive performance while remaining computationally efficient and more interpretable than deep learning approaches based on raw images.