Perbandingan Prediksi Penyakit Stunting Balita Menggunakan Algoritma Support Vektor Machine dan Random Forest

Stunting in toddlers is a serious health problem, especially in developing countries, where toddlers experience stunted growth due to chronic malnutrition. This condition not only affects the child's height but also their cognitive development and overall health. Identifying risk factors and classifying stunting can help in addressing and preventing this issue. In this study, we applied two machine learning methods to compare which one performs better in classification, namely Random Forest and Support Vector Machine (SVM), to classify stunting in toddlers. The data used is public data consisting of 97,873 entries. After undergoing preprocessing steps such as data cleaning, normalization, and splitting, the data was divided into training and testing sets. The Random Forest and SVM models were then trained using the training set and evaluated using metrics such as accuracy, precision, and recall. The analysis results showed that both methods perform well in classifying stunting in toddlers, with Random Forest achieving an accuracy of 0.9997 and SVM achieving an accuracy of 0.9951. These findings are expected to aid in the development of more effective intervention strategies to address stunting in toddlers. With this approach, it is hoped to make a significant contribution to reducing the prevalence of stunting in developing countries and improving the quality of life for children in the future. Additionally, this research opens opportunities for further exploration of other machine learning techniques for other health issues.