Prediction of Stunting Nutritional Status in Toddlers Using Naïve Bayes Classifier Algorithm

Abstract

Stunting is a chronic nutritional problem in toddlers that affects children's physical growth and cognitive development. Early identification and prediction of toddlers' nutritional status are crucial for timely intervention. This study aims to predict the nutritional status of stunting in toddlers using the Naïve Bayes Classifier algorithm. The data used in this study is derived from community health surveys with variables such as age, weight, height, and parental nutritional status. The research process began with data collection and pre-processing to ensure high-quality data. Subsequently, the data was trained using the Naïve Bayes Classifier algorithm, known for its simplicity and efficiency in data classification. Prediction results were then evaluated using metrics of accuracy, precision, recall, and F1-score to measure the model's performance. The study results indicate that the Naïve Bayes Classifier algorithm has high accuracy in predicting stunting status in toddlers, with an accuracy rate of 85%. Precision and recall also showed satisfactory results, at 82% and 87%, respectively. This model can be used as a tool for health workers to identify toddlers at risk of stunting, enabling earlier preventive measures. In conclusion, the use of the Naïve Bayes Classifier algorithm is proven effective in predicting the nutritional status of stunting in toddlers. The implementation of this model is expected to support child health programs and accelerate the reduction of stunting prevalence in the community.