Abstract
The proliferation of artificial intelligence systems in educational contexts has raised critical concerns regarding algorithmic fairness and demographic bias in student performance prediction. Traditional machine learning models, while achieving high predictive accuracy, often perpetuate or amplify existing disparities across gender, ethnicity, and socioeconomic backgrounds. This paper introduces a novel fairness-aware policy gradient framework that integrates demographic parity constraints into reinforcement learning architectures for student performance forecasting. Our approach employs constrained policy optimization to balance prediction accuracy with fairness metrics, utilizing a dual-objective reward function that penalizes discriminatory predictions while maintaining educational relevance. Through comprehensive experiments on diverse student datasets, we demonstrate that policy gradient methods with fairness constraints achieve superior bias mitigation compared to conventional supervised learning approaches, reducing demographic disparity by an average of 37.4% while preserving predictive performance within 2.8% of baseline models. The proposed framework incorporates adaptive fairness thresholds that dynamically adjust based on observed demographic distributions, enabling robust performance across heterogeneous educational environments. Our findings suggest that reinforcement learning-based fairness mechanisms provide a viable pathway for developing equitable AI systems in education while maintaining operational effectiveness for academic intervention strategies.
References
Asad, M. M., & Sohail, N. (2026b). Vlog marketing and customer decision-making: A review of the mediating roles of customer engagement and brand perception in the Malaysian context. An integrative literature review and conceptual framework. Asian Journal of Research in Business and Management, 3(1).
Salhab, M. A., Sohail, N., & Ali, D. A. (2025). The impact of AI-driven tools on production efficiency and quality management with Cascadeur software. In 2025 International Conference on Metaverse and Current Trends in Computing (ICMCTC). IEEE. https://doi.org/10.1109/ICMCTC62214.2025.11196350
Kayitesi, P. J., & Sohail, N. (2026). Barriers and enablers affecting women entrepreneurs in Rwanda: Evidence from women avocado exporters in Kigali City. Asian Journal of Economics, Business and Accounting, 26(6), 167–183. https://doi.org/10.9734/ajeba/2026/v26i62298
Mousumi, A. (2026). Service quality, engagement, and loyalty in Malaysian telecom. International Journal of Business and Social Science Studies, 6(1).
Asad, M. M., & Sohail, N. (2026a). The influence of vlog marketing on consumer purchase decision-making in Malaysia: The mediating role of consumer engagement. Global Media and Social Sciences Research Journal, 7(2).

This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2026 Ingrid Solheim, Marco De Santis (Author)