Analisis Data Resiko Stunting pada Puskesmas Kelurahan Jatiluhur Kota Bekasi Menggunakan Random Forest

Abstract

Stunting is one of the chronic nutritional problems that has a long-term impact on children's growth and development, especially in areas with limited access to health services and nutritional information. This study aims to predict the risk of stunting using a data mining approach with the Random Forest algorithm, with a case study at the Jatiluhur Village Health Center, Jatiasih District, Bekasi City. This research method uses a quantitative approach, which includes collecting primary data of 85 children, data preprocessing using Microsoft Excel, and modeling and testing using RapidMiner Studio with cross validation. The results of the study showed that the Random Forest algorithm was able to classify the risk of stunting accurately, with an accuracy value of 96.53%, recall reaching 98.61%, and precision of 100% for the stunting category. These findings indicate that machine learning technology can be an effective tool in supporting medical decision-making and more targeted nutritional interventions in primary health care facilities. This study contributes to the use of predictive analytics technology in the field of public health, especially in efforts to prevent and overcome stunting more efficiently and based on data. Keywords: Stunting, Random Forest, RapidMiner, Data Mining, Nutritional Risk Prediction.