In today's world, child mortality caused by malnutrition is on the rise. Due to the COVID-19 epidemic, armed conflict, and climate change, more children are going hungry than ever, and more than about 3 million children (about the population of Arkansas) die from malnutrition every year. Also, every year, 45 million children (about twice the population of New York) worldwide suffer from severe malnutrition. Our goal is to use a machine-learning approach for predictive modeling. We can determine the malnutrition condition of children who are five years old or younger by analyzing a set of malnutrition characteristics data. The dataset, consisting of 837 child records, was obtained from Kaggle which is an online platform that offers data science and machine learning repositories. As a component of the task, we assessed how well various machine learning techniques, including Random Forest, Gradient Boosting, Decision Tree, and XGB Classifier, functioned. The evaluation considered several factors, including children's gender, age, weight, and height. The dataset was divided into two parts, one for training and the other for testing. The training section contained 80% of the data while the remaining 20% was allocated for validation. The Gradient Boosting model performed the best in terms of accuracy, achieving a score of 97.61%. XGB classification had the second-best accuracy at 97.31%, followed by Decision Tree at 97.16%, and Random Forest at 96.11%.