Predicting and Forecasting University Rankings in the UAE using Machine Learning

Higher Education Institutions (HEIs) play a vital role in advancing knowledge economies, and institutional rankings are increasingly used as global benchmarks of academic performance and reputation. In the context of the United Arab Emirates (UAE), enhancing institutional competitiveness in global rankings aligns with national strategies such as UAE Vision 2030 and the Centennial Plan 2071. This research applies machine learning (ML) techniques to develop predictive models that forecast institutional ranking outcomes, enabling data-driven planning and continuous academic improvement. The study utilizes a dataset compiled from the QS World University Rankings (2020–2024), cross- referenced against the institutional listings maintained by the Commission for Academic Accreditation (CAA) to ensure alignment with the UAE’s accredited higher education landscape. It includes over 4,000 records covering performance metrics such as research output, faculty- student ratios, academic and employer reputation, international collaborations, sustainability, and graduate employability. Preprocessing steps included normalization, handling of missing values, and feature selection to improve modeling accuracy and robustness. Five machine learning algorithms were implemented in this study: XGBoost Tree, Neural Network, Linear Support Vector Machine (LSVM), Linear Regression, and Generalized Linear Model (GLM), to analyze institutional performance and predict global ranking placement. Among them, the XGBoost model achieved the highest predictive performance, reaching an correlation of 95%, indicating strong reliability in capturing institutional ranking dynamics. The evaluation focused on correlation coefficients, MSLE (Mean Squared Logarithmic Error), and feature importance analysis, providing a comprehensive assessment of predictive accuracy and the relative influence of institutional variables. To support future institutional planning, this study proposes the use of a dynamic dashboard that could visualize ranking trends and simulate the impact of performance indicators on predicted outcomes. Such a tool would enable university leaders to make timely, data-informed decisions and strengthen alignment with international benchmarks. This research highlights the potential of integrating machine learning into higher education strategy. By leveraging historical ranking data and performance indicators, the proposed approach supports predictive decision-making and long-term academic advancement. It is particularly relevant to UAE universities seeking to reinforce their international standing and fulfill national education and innovation goals. Future research may expand the framework to incorporate real-time institutional data, apply it to multiple global ranking systems, and extend comparative models across regional higher education landscapes. The findings demonstrate how machine learning can serve as a powerful enabler of foresight, excellence, and strategic planning in the higher education sector.