Klasifikasi Status Gizi Balita Menggunakan Algoritma Support Vector Machine dengan Optimasi Grid Search Cross-Validation

Toddlers are children aged 0 to 59 months who experience rapid growth and development and require a higher intake of nutrients. This study aims to classify the nutritional status of toddlers using the Support Vector Machine (SVM) algorithm with Grid Search optimization. The quality of a toddler's nutrition significantly affects their growth and development, and malnutrition is a major issue in Indonesia. Data were obtained from Posyandu Desa Jagalempeni, comprising a total of 512 toddler data entries. After undergoing pre-processing and feature engineering, the data were classified using SVM. The initial results showed an accuracy of 80%. Following the application of Grid Search optimization with the Radial Basis Function (RBF) kernel, accuracy increased to 86.17%. These results indicate that Grid Search is effective in optimizing SVM model parameters and improving classification performance.