<![CDATA[Stunting is a major nutritional issue in Indonesia that significantly impacts children's physical growth, cognitive development, and future quality of life. Childhood stunting can be identified using nutritional status indicators—such as weight-for-age (W/A), height-for-age (H/A), and weight-for-height (W/H)—specifically by observing a Z-score below -2 for the H/A indicator. The growing volume of anthropometric data on children under five necessitates a rapid and objective method for identifying stunting status. This study aims to classify children's stunting status using the K-Nearest Neighbor (KNN) algorithm based on growth data from children under five in East Lombok Regency, West Nusa Tenggara. The dataset comprises records for 3,416 children, including information on gender, age, weight-for-age (W/A), weight-for-height (W/H), and height-for-age (H/A). Data preprocessing involved removing duplicates, handling missing values, transforming categorical data, and applying Min-Max normalization. The data was split into 70% training data and 30% testing data, with the KNN algorithm applied using k = 5. Model evaluation was conducted using a confusion matrix. The results demonstrate that the KNN model achieved an accuracy rate of 83.15%, indicating a strong capability to classify stunting status based on the children's anthropometric characteristics. These findings confirm that the KNN algorithm can serve as a tool for healthcare professionals to identify stunting more rapidly, objectively, and efficiently, thereby supporting early prevention and management efforts.]]>
Copyrights © 2026
