Falls pose a significant threat to the elderly population, often resulting in severe health complications such as fractures and other adverse outcomes, which can drastically lower their quality of life. Early detection of fall risks is crucial in mitigating the impact of such events. Various technologies have been developed to address this issue, including alert systems that notify users of imminent dangers due to environmental factors or physiological changes. However, accurately detecting and distinguishing between normal activities, imminent risk of falling, and actual falls remains challenging. This study proposes a machine learning approach using the XGBoost algorithm to improve fall detection accuracy among the elderly. A dataset comprising 2,039 samples, categorized into normal, imminent risk of fall, and fall classes, was utilized to train and test the model. The model was trained on 70% of the data, with 30% allocated for testing. Hyperparameter optimization was performed using a randomized search with cross-validation. The optimal parameters were then employed to train the model, achieving an overall accuracy of 96.67%. The confusion matrix demonstrates the model's robust ability to distinguish between the three classes with minimal false positives. Additionally, sensitivity tests were conducted by varying training sample sizes and randomizing data splits, confirming the model’s robustness in different conditions. These results show that the proposed method outperforms previous studies in detecting fall-related events, reducing the likelihood of false alarms and enhancing resource allocation for elderly care.