<![CDATA[Stunting is a serious public health issue with long-term impacts on human resource quality and the achievement of the Sustainable Development Goals (SDGs), including in Jambi Province. This study aims to analyze the contributing factors of stunting using a Machine Learning approach, specifically the Backpropagation Neural Network Regression method. The data used were obtained from the Jambi Province Central Bureau of Statistics in 2021, with independent variables including the percentage of infants not exclusively breastfed, poor sanitation access, pneumonia cases among children under five, tuberculosis cases, and the percentage of the poor population. The dependent variable is the percentage of stunted children under five. The study found that the best architecture was achieved with a learning rate of 0.01 and a network structure of 3-8-4-1-11, producing the lowest values of Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE), at 0.598, 0.773, and 0.63, respectively. This model is capable of identifying hidden indicators (hidden layers) from each stunting factor, which can be used to design more effective policy interventions. The study concludes that the application of Machine Learning can be an innovative solution to support strategic decision-making in reducing stunting rates in Jambi Province.]]>
Copyrights © 2025
