<![CDATA[Stunting is a serious health issue caused by insufficient nutrition over an extended period, especially in young children. This study aims to develop a web-based stunting data classification system using a combination of K-Means Clustering and K-Nearest Neighbors (K-NN) algorithms. The dataset used is sourced from the Health Department of Medan City in 2021-2024, consisting of 683 data entries. The research process includes problem identification, data gathering conducted through observations and interviews, data preprocessing using StandardScaler, and splitting the dataset into 70% training and 30% testing datasets. The K-Means technique is utilized for data segmentation based on z-score values. The clustering results are then used as labels for classification with K-NN. The system implementation shows a classification result with a distribution of 6.9% for mild stunting, 25.8% for moderate stunting, and 67.3% for severe stunting. The results indicate that the combination of K-Means and K-NN produces more accurate classification compared to using a single method. This study is expected to assist the Health Department of Medan City in analyzing stunting data more efficiently and contribute to the future development of stunting classification systems.]]>
Copyrights © 2025
