Malnutrition is a significant public health issue, particularly in developing countries, and Ethiopia is no exception. Due to this, we have developed a prediction of malnutrition status among children under the age of five in Ethiopia using a deep learning approach. The prevalence of malnutrition in Ethiopia is alarming, with high rates of stunting, underweight, wasting, and overweight. The objective of this study is to develop a predictive model that can identify children at high risk of malnutrition using deep learning algorithms. By analyzing relevant factors such as age, height, weight, wealth index, maternal education, and other healthcare indicators. The proposed model aims to improve the understanding and prediction of malnutrition status. The study also focuses on the importance of addressing malnutrition through data-driven approaches and emphasizes the potential of deep learning in this context. The deep learning techniques that are suitable for our malnutrition status prediction model using a secondary dataset from (EDHS). The study used a deep learning algorithm ANN and the other four machine learning algorithms among them ANN 91.7%, DT 90.2%, LR 89%, RF 91`%, and SVM 81.7%, and compared the result. When we look at the results, we observe that ANN outperformed the other four machinelearning methods. We would like to recommend predicting the malnutrition status by using deep learning approaches to compare with our results and using more sample sizes as well increase the predictive variables and using the image dataset. The findings of this research can contribute to the development of effective interventions and policies to combat malnutrition among children in Ethiopia