OBESITY RISK CLASSIFICATION BASED ON GRADIENT BOOSTING USING MEDICAL DATA

Abstract

Obesity is a growing global health issue that significantly contributes to the development of chronic diseases such as diabetes, cardiovascular disorders, and metabolic syndromes, making early detection essential to support preventive healthcare strategies. This study aims to implement the Gradient Boosting algorithm to classify obesity risk based on medical data obtained from the UCI Machine Learning Repository, which includes information on eating habits, physical activity, and individual characteristics. The research methodology involves several stages, including data preprocessing, transformation, normalization, class mapping, and dataset splitting into training and testing sets with a ratio of 70:30. The Gradient Boosting model is constructed using multiple decision trees in an iterative manner to improve classification performance, categorizing individuals into obese and non-obese classes. Model evaluation is conducted using accuracy, precision, recall, and F1-score metrics. The experimental results indicate that the model achieves an accuracy of over 90%, with a relatively small gap between training and testing performance, demonstrating good generalization capability without overfitting. These findings confirm that Gradient Boosting is an effective approach for obesity risk classification and has strong potential to support intelligent healthcare systems in enabling data-driven decision-making for early prevention and treatment.