<![CDATA[Stunting is a condition characterized by impaired growth in toddlers caused by prolonged nutritional deficiency, which negatively affects physical development, cognitive capacity, and long-term productivity. Early identification of nutritional status using a data-driven classification approach serves as an essential strategy to prevent stunting, particularly in rural areas such as Sendang Dajah Village where access to health services is limited. This study aims to develop a nutritional status classification model for toddlers and generate food combining recommendations tailored to each child’s nutritional needs. The research variables include age, height, weight, and gender. The classification model was constructed using the Support Vector Machine (SVM) algorithm with an 80% training and 20% testing data split. The dataset consists of 300 toddler samples collected through Posyandu and field surveys. The experimental results indicate that SVM successfully classified nutritional status into four categories Severely Stunted, Stunted, Normal, and Tall with an accuracy of 95%, macro average precision of 0.95, recall of 0.96, and f1-score of 0.95, and weighted average precision of 0.96, recall of 0.95, and f1-score of 0.95. These findings demonstrate that SVM is an effective predictive method for early stunting detection and can serve as a decision-support tool for healthcare workers and parents in planning appropriate nutritional interventions.]]>
Copyrights © 2025
