Implementation of Artificial Neural Network (ANN) to Construct Model for Stunting in Toddlers

Malnutrition in children under 5 years is a crucial problem in Indonesia. Stunting is a condition of malnutrition that affects children's growth and development. From health data, several factors that influence (risk factors) the condition of stunting. Some of the factors are gender, birth weight, birth height, age, weight by age, weight according to height, upper arm circumference, and height for age. A series of processes in this research are handling missing values by imputation, ranking features based on importance values and classifying the combination of risk factors that cause stunting using the Artificial Neural Network (ANN) method. The results of this study are the formation of a model to determine stunting status in early detection of stunting in children under 5 years of age (toddlers). Research shows that the stunting generalization model uses the best ANN method when using a test size of 0.2 and the number of hidden layers used is 2 with 32 nodes each. The best model is shown by a combination of 4 important features.