STUNTING PREDICTION MODEL IN TODDLERS USING THE NAÏVE BAYES

Abstract

This study investigates the use of Naive Bayes algorithm for child stunting classification based on health and nutrition data. This study aims to identify factors that influence the risk of stunting and develop a predictive model that can assist in stunting prevention and intervention. The research methodology includes initial data processing, division of the dataset into training and testing sets, model training using the Naive Bayes algorithm, and evaluation of model performance through metrics such as accuracy, precision, and recall.

The results showed that the Naive Bayes model achieved an accuracy of 72.49% for training data and 81.25% for testing data. Confusion matrix analysis shows a precision value of 0.911 and recall of 0.710 for training data; for testing data, the precision value is 0.914 and recall is 0.842. The results show that the Naive Bayes model is able to perform stunting classification quite well, although there are some limitations, such as the conditional independence assumption that may not be met at all times. This research provides insight into how classification models can be used in public health, particularly in efforts to detect and prevent stunting. The results are promising, but further evaluation is needed to optimize the model and ensure that it can be used effectively in the real world.