<![CDATA[Nutritional problems in children under five remain a major challenge in Indonesia's health development as they can affect growth, cognitive abilities, and future productivity. The Indonesian Nutritional Status Survey (SSGI) serves as an important data source to understand the nutritional condition of children under five. This study aims to classify the nutritional status of children under five using the Random Forest algorithm with a Knowledge Discovery in Database (KDD) approach. The research stages include data cleaning, preprocessing, feature selection, modeling, and model performance evaluation. The data were obtained from Puskesmas Gang Sehat.The results indicate that Random Forest can classify the nutritional status of children under five with high accuracy for the majority class (Normal Nutrition), while performance for the minority class (Abnormal Nutrition) can still be improved. This demonstrates that the Random Forest algorithm is effective for classifying nutritional status, although optimizing data imbalance and adding supporting variables can enhance results for the minority class. This study is expected to contribute to the development of technology-based solutions for addressing nutritional issues in children under five.]]>
Copyrights © 2026
