In the context of the digital transformation of higher education, the role of data analytics in supporting academic decision-making is becoming increasingly significant. This paper proposes a conceptual and methodological framework for the development of interpretable analytical dashboards within the domain of Learning Analytics for smart universities. Particular attention is given to the integration of machine learning methods and Explainable Artificial Intelligence (XAI) to ensure transparency and interpretability of analytical models. The study introduces a multi-stage analytical pipeline that includes data collection and preprocessing, predictive model construction, model interpretation, and visualization of results through interactive dashboards. Machine learning algorithms, including Random Forest, are employed for predictive modeling, while SHAP and LIME methods are used to interpret the results. Experimental validation was conducted on a dataset of student records containing both academic and behavioral indicators. The results demonstrate high effectiveness of the proposed approach, with performance metrics of AUC ≈ 0.89, Accuracy = 0.87, and F1-score = 0.84, confirming the model’s ability to accurately identify at-risk students. Interpretability analysis revealed that the most influential factors include academic performance (GPA), LMS activity level, and participation in educational interactions. Usability evaluation using the System Usability Scale (SUS) indicated a high level of user experience (SUS = 82). A comparative analysis with traditional approaches shows a significant advantage of the proposed system in terms of accuracy, interpretability, and visualization. Thus, the proposed analytical dashboard not only ensures high predictive performance but also enhances transparency, facilitating more informed academic decision-making. Overall, the study confirms that the integration of Learning Analytics, XAI, and visual analytics enables the development of effective decision-support systems capable of improving educational quality in smart universities.