<![CDATA[Stunting is a significant nutritional problem that negatively impacts children’s physical and cognitive development, especially in poor countries like Indonesia. This study used the XGBoost algorithm to examine stunting data in children under the age of five. The analysis results showed that XGBoost processed complex datasets quickly and produced accurate predictions, achieving a model performance evaluation with 86 percent accuracy, 89 percent precision, 95 percent recall, and 92 percent F1 score. This approach effectively found significant trends for early stunting identification through the utilization of body mass index (BMI) and other anthropometric data, which conventional methods failed to reveal. This study also presents opportunities for advancement in the Internet of Things (IoT) framework to improve the efficacy of real-time stunting detection systems. IoT devices provide more precise and reliable anthropometric data collection, thereby improving the efficacy of the XGBoost model in estimating stunting risk. Although IoT applications were not the primary focus of this study, its findings provide substantial contributions to the advancement of data science and technology in the healthcare sector, particularly in initiatives aimed at preventing stunting. This research offers theoretical contributions to the development of data science and health technology, as well as practical benefits in the form of data-based solutions that can be integrated into national programs to reduce the prevalence of stunting, to support more targeted nutritional interventions and improve the quality of life of children in Indonesia.]]>
