Prediksi Risiko Stunting Pada Anak Berdasarkan Sanitasi Lingkungan Tinggal Menggunakan Random Forest

Abstract

Stunting is a health problem influenced by various factors, one of which is the residential environmental sanitation. While stunting has been linked to growth development and nutritional intake, environmental sanitation factors tend to receive less attention. Environmental sanitation in this study includes the availability of clean water, proper sanitation facilities, waste disposal systems, and the overall cleanliness of the living environment. This research aims to build a predictive model for stunting risk in children based on environmental sanitation variables using the Random Forest method. This method is a classification algorithm that constructs multiple decision trees to improve prediction accuracy. The dataset consists of environmental condition data and children's nutritional status, which have undergone preprocessing and variable transformation. The modeling process was conducted by splitting the data into training and testing sets, then evaluated using accuracy and F1-score metrics. The results indicate that the model can classify stunting risk with an accuracy rate of 85% and identify the most influential sanitation variables. This model is expected to support decision making tool for data driven stunting prevention efforts.