Applying Big Data and Artificial Intelligence Analytics to Assess and Forecast Educational Quality

This analytical study investigates how big data and artificial intelligence (AI) can support educational quality assessment and forecasting within higher education, including language-for-medical-purposes instruction. A structured narrative synthesis of policy documents and foundational peer-reviewed research is employed to define quality indicators, examine predictive modelling options, and develop a responsible implementation framework. The findings identify five interconnected components: interoperable data collection, validated indicators, transparent prediction, educator-led intervention, and independent impact evaluation. Two tables and two illustrative diagrams clarify the functional differences between reporting, learning analytics and AI-assisted decision support. The paper does not claim that an institutional model has been trained or validated. It concludes that predictive accuracy alone is insufficient: meaningful educational improvement requires fairness checks, privacy protection, human oversight and demonstrated benefits to learning outcomes.