ARCHIVES

Abstract: This study proposes a data science machine learning approach to predict malnutrition status in children under five years old, a significant health issue affecting a country's economic growth. Utilizing training datasets from Kaggle, hidden factors are extracted using machine learning techniques, and classification algorithms such as Bayesian classifier and K-nearest neighbor are employed for prediction. The system is built as a real-time application using Visual Studio as the front-end technology and SQL Server as the back-end technology, demonstrating the accuracy of data science classification techniques in predicting malnutrition status based on clinical datasets.