<![CDATA[Stunting is a condition of inhibited linear growth due to chronic malnutrition, which is a serious concern in Indonesia, especially among toddlers. Stunting identification utilizes the parameter of height-for-age z-score (HAZ), with a value of less than -2 SD as a diagnostic indicator. Factors such as socioeconomic conditions, dietary patterns, infections, and the environment influence stunting, making early prevention and intervention efforts crucial. Short-term effects of stunting include delayed motor development and cognitive impairment, while long-term impacts include the risk of chronic diseases in adulthood. Although the global prevalence of stunting has declined, Indonesia still has a high rate, ranking second in Southeast Asia. Cross-sector collaboration and the application of technology, such as Support Vector Machine (SVM) algorithms, can help identify stunting risk factors. In this study, SVM kernels including linear, polynomial, RBF, and sigmoid were evaluated. RBF SVM kernel proved to be the most effective, achieving an accuracy of over 90% with an AUC of 0.926. Collaboration and the use of technology provide hope for addressing stunting in Indonesia, requiring cooperation between the government, NGOs, and the scientific community]]>
Copyrights © 2024
