Predicting and understanding student academic outcomes is crucial for enhancing educational interventions and fostering student success. Explainable Artificial Intelligence makes machine learning models not only perform well but also transparent and trustworthy. This paper presents the application of explainable machine learning techniques to predict and interpret academic performance in higher education. Experiments have been carried out on a students’ dataset using several machine learning algorithms, including Logistic Regression, Singular Value Decomposition, Decision Trees, Random Forest, and Naive Bayes. The performance of these models is assessed using Precision, Recall, and F-score metrics to determine their predictive accuracy. The results indicate that the Random Forest model can accurately predict academic performance with high precision, using variables such as demographic data and academic history. To illustrate how explainable recommendations can be generated, the model that presents the best performance in the most metrics evaluated was selected.