AI-Enabled Smart Education System Using Artificial Intelligence and Predictive Analytics

The increasing use of digital technologies in education has generated large volumes of academic data that can be utilized to improve student learning outcomes and institutional decision-making. Traditional student performance prediction systems often provide accurate results but lack transparency, making it difficult for educators to understand the reasons behind predictions. This paper proposes an Explainable Artificial Intelligence (XAI) framework for predicting student academic performance while providing clear and interpretable explanations for prediction outcomes. The system analyzes student-related data such as attendance records, internal assessment marks, assignment submissions, and learning activities using machine learning algorithms including Random Forest, Decision Tree, and XGBoost. To improve transparency and trust, Explainable AI techniques such as SHAP (SHapley Additive Explanations) and LIME (Local Interpretable Model-Agnostic Explanations) are integrated into the framework to identify the most influential factors affecting student performance. The proposed system helps faculty members detect at-risk students at an early stage and take appropriate academic interventions. Experimental results demonstrate that the model achieves high prediction accuracy while maintaining interpretability and reliability. The framework supports data-driven educational management, enhances academic monitoring, and promotes informed decision-making, thereby contributing to the development of intelligent, transparent, and effective smart education systems.