Data-Driven Efficiency Analysis of EU Higher Education Systems Using Stochastic Frontier Models

Abstract

This study investigates the efficiency of higher education systems across the 27 Member States of the European Union during the period 2017–2022, addressing increasing policy interest in data-driven decision support and optimization techniques for performance evaluation in education systems. Efficiency is assessed using Stochastic Frontier Analysis, an optimization-based econometric approach, applied to multiple output dimensions relevant to learning analytics: alignment between graduates’ skills and labour market requirements, scientific productivity measured by published articles, and the number of higher education graduates. The model incorporates key input variables, including the student–teacher ratio, public expenditure per student, research and development expenditure, and the number of academic staff, while controlling for real gross domestic product per capita. To support integrated efficiency measurement and information-based decision-making, multidimensional outcomes are aggregated into composite efficiency indices using entropy-based weighting. The results reveal substantial cross-country heterogeneity in efficiency across EU higher education systems, identifying a cluster of high-performing countries that consistently optimize scientific output and graduate production. Financial resources and academic staff availability emerge as significant drivers of efficiency, while skill matching to labour market demand remains a persistent structural challenge. By combining Stochastic Frontier Analysis with entropy-based aggregation, this study provides a robust data-driven decision support framework for efficiency assessment, offering valuable insights for education policy design, resource allocation, and learning-oriented system optimization.