<![CDATA[Obesity in adolescents is a growing public health concern due to its association with various chronic diseases such as type 2 diabetes, hypertension, and metabolic disorders. This study aims to develop an obesity risk prediction system for adolescents based on dietary patterns and physical activity data using the Random Forest algorithm. The data was obtained from a secondary dataset available on the Kaggle platform, comprising 2,111 entries and 17 features covering dietary habits, physical activity, and anthropometric characteristics. The Random Forest method was chosen for its ability to handle high-dimensional data and produce accurate classifications. The developed system is a console-based application where users can input their lifestyle data and receive obesity risk predictions in three levels: low, moderate, and high. Model performance evaluation showed excellent results with an accuracy of 95%, as well as consistently high precision, recall, and F1-score values. Compared to other algorithms such as KNN and Decision Tree, Random Forest demonstrated competitive and stable performance. The results of this study are expected to be utilized as an educational and preventive tool for early detection of obesity risk in adolescents.]]>
Copyrights © 2025
