Klarifikasi Status Penderita Gizi Sunting Pada Balita Menggunakan Metode Random Forest

Stunting in children, as in this case, is characterized by lower-than-average body growth. This is caused by a mismatch between long-term nutrient intake and the body's needs. Possible impacts include delayed cognitive development, impairments in learning ability, as well as an increased risk of metabolic syndrome. To overcome these problems, a structured and data-based system is needed with one of the agreements used, namely the Random Forest Method on the system using stunting nutrition data for toddlers as the basis for the classification process. In developing the system that was built to help track the health of young children, especially stunting by using several indicators to support innovation, provide a classification model for toddlers suffering from stunting nutrition, and measure and evaluate the performance results of the Random Forest Method against the data variables used. From this study, it can be shown that the results of this study are that this system has successfully made a classification model and is very effective in measuring and evaluating the performance results of the Random Forest Method in the Status Classification of Stunting Nutritional Patients in Toddlers by using a dataset of 300 data so that it produces an average accuracy of 81%, an average result of 76%, an average recall result of 69%, and the average F1 score result is 72%.