Obesity is a global health issue with a continuously increasing prevalence. Early prediction of obesity levels is crucial for designing more effective intervention strategies. This study aims to apply and analyze the performance of three machine learning classification methods: Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression (LR), for predicting obesity levels. The research methodology utilizes a public dataset, ObesityLevels, downloaded from the Kaggle platform, which consists of 2111 medical and lifestyle records. The process includes data preprocessing to convert categorical features into numerical ones, splitting the data into training and testing sets with a 70:30 ratio, model training, and evaluation using accuracy, precision, recall, and F1-score metrics. The results indicate that the Random Forest (RF) algorithm achieved the highest performance, with an accuracy of 90.3%, precision of 90.3%, recall of 90.3%, and an F1-score of 90.3%. Based on these findings, it is concluded that the Random Forest model is the most effective choice for an obesity level prediction system based on the dataset used.