Visualisasi Prediksi Prevalensi Balita Menggunakan Algoritma Random Forest Pada Lembaga Bidang Pangan

Abstract

This study aims to apply the Random Forest algorithm to predict the prevalence of malnutrition in toddlers in DKI Jakarta. This algorithm was chosen because it has been proven to provide high prediction accuracy, with an average above 80% in previous research. The research method includes stages of problem formulation, research objectives, research design, sample selection, data collection, data processing, interpretation of results, report preparation, and result presentation. The data used is sourced from the National Food Agency (BPN) totaling 3000 datasets, which are then processed through stages of selection, preprocessing, transformation, data mining using the Random Forest algorithm, and evaluation using RMSE and MAE formulas. It is expected that the results of this study will provide valuable insights into efforts to address malnutrition issues in toddlers in the DKI Jakarta area.

Keywords: Prediction ,Random Forest, Prevalence of Toddlers,Nutrition