Early Prediction of Obesity Levels Using Machine Learning

Obesity is a growing global health issue, closely linked to various chronic diseases. Accurate estimation of obesity levels is essential for early intervention and effective management. This project focuses on using machine learning techniques to estimate obesity levels based on diverse health and lifestyle factors, such as age, gender, physical activity, and dietary habits. The model predicts an individual's obesity level. The dataset used for this research contains various attributes related to health, nutrition, and physical activity. To prepare the data, preprocessing techniques, including label encoding for categorical features, are applied. We implement the XGBoost algorithm to predict obesity levels. Our findings demonstrate that the XGBoost algorithm achieves greater accuracy, making it the most suitable for estimating obesity levels. Model performance is evaluated using accuracy, precision, recall, and F1-score metrics. This project highlights the importance of integrating machine learning in public health initiatives, aiming to address obesity more effectively and reduce its associated health risks