Malnutrition remains one of the most pressing global health challenges, particularly in developing countries like Bangladesh, where it continues to significantly impact child health and contribute to chronic illness and high child mortality. Despite the potential of machine learning to improve malnutrition predictions, research in this area remains limited in the country. This study utilizes Bangladesh Demographic and Health Survey (BDHS) 2022 data to identify and quantify key determinants of under-five malnutrition (underweight, wasting, stunting) and evaluates various machine learning models for predicting malnutrition. By addressing a critical gap, this research provides deeper insights into the root causes of malnutrition in Bangladesh. Descriptive statistics were conducted to summarize the key characteristics of the dataset. Boruta algorithm was employed to identify important features related to malnutrition which were then used to evaluate several machine learning models, including K-Nearest Neighbors (KNN), Neural Networks (NN), Classification and Regression Trees (CART), XGBoost (XGBM), Support Vector Machines (SVM), and Random Forest (RF), in addition to the traditional logistic regression (LR) model. The best-performing model was selected to identify the most important factors contributing to malnutrition. The significance of these variables was further assessed using Feature Importance plot (Based on Gini Importance) and Shapley Additive Explanation (SHAP) values. Model performance was evaluated through various metrics, including accuracy, 95% Confidence Interval (CI), Cohen's kappa, sensitivity, specificity, F1 score and precision. The study examined a cohort of 7,910 children, reporting prevalence rates of 19% for stunting, 8% for wasting, and 17% for underweight. The Boruta algorithm identified 18 confirmed features for stunting, 22 for wasting, and 19 for underweight. For stunting, the Random Forest (RF) model outperformed other methods with an accuracy of 64.19%, 95% CI of (0.623, 0.666), Cohen's kappa of 0.158, sensitivity of 56.25%, specificity of 66.00%, F1 score of 0.750 and precision of 0.60. In wasting prediction, RF achieved the highest accuracy at 76.68%, 95% CI of (0.743, 0.787), Cohen's kappa of 0.049, sensitivity of 27.22%, specificity of 80.98%, F1 score of 0.865 and precision of 0.810. Similarly, for underweight, RF demonstrated superior performance with an accuracy of 68.18%, 95% CI of (0.662, 0.703), Cohen's kappa of 0.130, sensitivity of 43.02%, specificity of 73.48%, F1 score of 0.792 and precision of 0.735. Across all malnutrition types, the RF model consistently outperformed traditional logistic regression (LR) and other ML techniques in terms of accuracy, sensitivity, specificity, and other performance metrics. For stunting, key predictors identified in both the Shapley and Gini importance plots included mother's education, father's occupation, place of delivery, wealth index, birth order, and toilet facility; for wasting, significant predictors were antenatal care, unmet family planning, mother's BMI, birth interval, father's occupation, and television ownership; and for underweight, important factors included father's occupation, mother's education, child's age, birth order, wealth index, and place of delivery. This study highlights the effectiveness of Random Forest (RF) in predicting malnutrition outcomes-stunting, wasting, and underweight-using key features identified by the Boruta algorithm. While RF demonstrates moderate performance in predicting stunting and underweight, it shows strong predictive ability for wasting. This underscores RF's potential in guiding targeted interventions for wasting, though further improvements are needed for stunting and underweight predictions. Moreover, the study identifies key contributors for each malnutrition outcome. By pinpointing these determinants, the study provides actionable insights for designing targeted interventions to combat malnutrition more effectively. These findings align with the global development agenda, particularly Sustainable Development Goal (SDG) 2: Zero Hunger and SDG 3: Good Health and Well-being, reinforcing efforts to reduce malnutrition and improve child health outcomes in Bangladesh.