A Time-Adaptive Ensemble Framework for Multi-Year University Ranking Prediction Integrating Outlier-Aware Scoring and Hybrid Feature Selection
Keywords:
University Ranking Prediction, Time-Adaptive Ensemble, Outlier-Aware Scoring, Hybrid Feature Selection, Multi-Year Forecasting, SHAP InterpretabilityAbstract
University ranking prediction requires adaptive models to capture temporal dynamics and handle data anomalies. This study develops a time-adaptive ensemble framework integrating outlier-aware scoring and hybrid feature selection. We collected data from Times Higher Education from 2011 to 2024, applying windowed outlier detection with clipping and masking, and using ANOVA F-tests, permutation importance, and SHAP values to select dynamic feature subsets. The framework trains linear moving-average, temporal Random Forest, and LSTM models, then ensembles their forecasts using dynamically optimized weights. Experimental results on rolling forecasts (2016–2024) demonstrate a mean rank deviation of 1.2 positions, Top-1000 classification accuracy of 0.96, and reduced MAE and RMSE compared to single-model baselines. SHAP-based analyses reveal evolving feature importance across time windows, highlighting the impact of changing indicators. The findings indicate that integrating outlier handling, dynamic feature selection, and ensemble learning enhances prediction robustness and interpretability. This framework can support strategic decision-making, policy formulation, and resource allocation in higher education
References
Abramo, G., & D’Angelo, C. A. (2015). Evaluating university research: Same performance indicator, different rankings. Journal of Informetrics, 9(3), 514-525.
Agarwal, N., & Tayal, D. K. (2022). FFT based ensembled model to predict ranks of higher educational institutions. Multimedia Tools and Applications, 81(23), 34129-34162.
Ahmed, A. M., Mohammed, C. N., & Ali, S. H. (2024). An Innovative Deep Neural Network Model for Precise Calorie Burn Prediction from Physical Activity Data. International Journal of Informatics, Information System and Computer Engineering (INJIISCOM), 5(2), 264-275.
Baltaru, R. D., Manac, R. D., & Ivan, M. D. (2022). Do rankings affect universities’ financial sustainability?–financial vulnerability to rankings and elite status as a positional good. Studies in Higher Education, 47(11), 2323-2335.
Basireddy, C. S., Cheruku, V. K. G., Rajagopal, S., & Soangra, R. (2024). Hybrid prediction models for assessing the higher education institutions performance in QS World Institution rankings. F1000Research, 13, 1529.
Beyaztas, U., & Shang, H. L. (2019). Forecasting functional time series using weighted likelihood methodology. Journal of Statistical Computation and Simulation, 89(16), 3046-3060.
Dearden, J. A., Grewal, R., & Lilien, G. L. (2019). Strategic manipulation of university rankings, the prestige effect, and student university choice. Journal of marketing research, 56(4), 691-707.
Estrada-Real, A. C., & Cantu-Ortiz, F. J. (2022). A data analytics approach for university competitiveness: the QS world university rankings. International Journal on Interactive Design and Manufacturing (IJIDeM), 16(3), 871-891.
Ghaddar, A., Thoumi, S., & Saab, S. S. (2024). Leveraging journal citation-based metrics for enhanced university rankings methodology. Frontiers in Research Metrics and Analytics, 9, 1510169.
Hyndman, R. J., & Rostami-Tabar, B. (2025). Forecasting interrupted time series. Journal of the Operational Research Society, 76(4), 790-803.
Iqbal, A., & Amin, R. (2024). Time series forecasting and anomaly detection using deep learning. Computers & Chemical Engineering, 182, 108560.
Kareem, A. R., & Abdullah, H. S. (2025). Business Intelligence Approach-Based Hybrid Deep Learning Model for QS World University Ranking. Iraqi Journal of Science, 375-387.
Karimian, M., & Beigy, H. (2023). Concept drift handling: A domain adaptation perspective. Expert Systems with Applications, 224, 119946.
Kim, S., Kim, H., & Hwang, Y. (2025). Data-driven dynamic response forecasting and anomaly detection in long-span bridges. Journal of Civil Structural Health Monitoring, 1-18.
Kurniawan, B., Meyliana, M., Warnars, H. L. H. S., Suharjo, B., & Ahiase, G. (2024). Bibliometric analysis using vos viewer with publish or perish of intelligent tutoring system in private universities. International Journal of Informatics, Information System and Computer Engineering (INJIISCOM), 5(2), 166-177.
Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in neural information processing systems, 30, 4765–4774.
Mazarei, A., Sousa, R., Mendes-Moreira, J., Molchanov, S., & Ferreira, H. M. (2025). Online boxplot derived outlier detection. International journal of data science and analytics, 19(1), 83-97.
McAleer, M., Nakamura, T., & Watkins, C. (2019). Size, internationalization, and university rankings: Evaluating and predicting Times Higher Education (THE) data for Japan. Sustainability, 11(5), 1366.
Moed, H.F. (2017) A critical comparative analysis of five world university rankings. Scientometrics, 110, 967–990.
Raufi, B., & Longo, L. (2024). Comparing ANOVA and PowerShap Feature Selection Methods via Shapley Additive Explanations of Models of Mental Workload Built with the Theta and Alpha EEG Band Ratios. BioMedInformatics, 4(1), 853-876.
Robinson-Garcia, N., Torres-Salinas, D., Herrera-Viedma, E., & Docampo, D. (2019). Mining university rankings: Publication output and citation impact as their basis. Research Evaluation, 28(3), 232-240.
Selten, F., Neylon, C., Huang, C. K., & Groth, P. (2020). A longitudinal analysis of university rankings. Quantitative Science Studies, 1(3), 1109-1135.
Soegoto, E. S., Ananta, H., Zaki, I., & Ranau, M. I. N. (2022). Implementation of management information system using machine learning technology. International Journal of Research and Applied Technology (INJURATECH), 2(2), 220-228.
Soegoto, Y., Meyliana, M., Prabowo, H., Hidayanto, A. N., Trisetyarso, A., & Pradipto, Y. D. (2023). Digital Transformation in Higher Education. International Journal of Research and Applied Technology (INJURATECH), 3(2), 300-307.
Tabassum, A., Hasan, M., Ahmed, S., Tasmin, R., Abdullah, D. M., & Musharrat, T. (2017, February). University ranking prediction system by analyzing influential global performance indicators. In 2017 9th International conference on knowledge and smart technology (KST) (pp. 126-131). IEEE.
Thakur, D., & Biswas, S. (2024). Permutation importance based modified guided regularized random forest in human activity recognition with smartphone. Engineering Applications of Artificial Intelligence, 129, 107681.
Tóth, B., Motahari-Nezhad, H., Horseman, N., Berek, L., Kovács, L., Hölgyesi, Á., Péntek, M., Mirjalili, S., Gulácsi, L. & Zrubka, Z. (2024). Ranking resilience: assessing the impact of scientific performance and the expansion of the Times Higher Education Word University Rankings on the position of Czech, Hungarian, Polish, and Slovak universities. Scientometrics, 129(3), 1739-1770.
Wisaeng, K., & Muangmeesri, B. (2025). University rankings prediction using hybrid feature selection based on machine learning methods. International Journal of Analysis and Applications, 23, 112.
