Artificial Intelligence and Machine Learning in Higher Education: Evaluating Strategies to Reduce Academic Disparities
DOI:
https://doi.org/10.64235/xq836s26Keywords:
Artificial Intelligence, Machine Learning, Higher Education, Academic Disparities, Early Warning Systems, Adaptive Learning, Predictive AnalyticsAbstract
Academic disparities — the systematic divergence in educational outcomes across student populations differentiated by socioeconomic background, geographic region, first-generation status, gender, and ethnicity — remain among the most persistent structural inequities in global higher education. Despite decades of institutional policy and targeted student support investment, the GPA gap between the highest- and lowest-risk student quintiles in large universities has narrowed by less than 8% over the past two decades using conventional approaches. Artificial Intelligence (AI) and Machine Learning (ML) now offer a fundamentally new toolkit for addressing this challenge: predictive modelling capable of early disparity identification, adaptive systems that personalise learning at scale, and automated intervention workflows that route support resources with a speed, precision, and continuity that human-only systems cannot sustain. This paper presents a comprehensive evaluation of five AI and ML strategy categories deployed across 36,400 students at six higher education institutions spanning India, Ghana, and Mexico over four academic years (AY 2022–26), constituting the longest and largest multi-site longitudinal evaluation of AI-ML disparity reduction strategies in the JSTST literature.
Downloads
References
Arnold, K. E., & Pistilli, M. D. (2012). Course Signals at Purdue: Using learning analytics to increase student success. Proceedings of LAK ‘12, 267–270.
Kaashifah, & Easton-Brooks, D. (2025). Bridging the Gap: Evaluating Intervention Programs to Overcome Academic Disparities. The Urban Review, 57(3), 670-688.
Venkata, S. B. (2026, March). Computational Forgetting: Algorithms for Safe Memory Reduction in Long-Lived Systems. In 2026 9th International Conference on Intelligent Computing and Control Systems (ICICCS) (pp. 1993-1999). IEEE.
MARASANI, Y. (2024). Enterprise Readiness for Generative AI: The Critical Role of Data Engineering. Frontiers in Computer Science and Artificial Intelligence, 3(2), 59-71.
Hardt, M., Price, E., & Srebro, N. (2016). Equality of opportunity in supervised learning. Advances in Neural Information Processing Systems, 29, 3315–3323.
MARASANI, Y. (2023). Machine Learning Models for Predicting Patient Treatment Switching Using Claims Data. Frontiers in Computer Science and Artificial Intelligence, 2(1), 59-66.
Jack, A. A. (2019). The Privileged Poor: How Elite Colleges Are Failing Disadvantaged Students. Harvard University Press.
Kizilcec, R. F., & Lee, H. (2022). Algorithmic fairness in education. In The Ethics of Artificial Intelligence in Education (pp. 174–202). Routledge.
Marasani, Y. (2025). Explainable AI Frameworks for Patient-Level Claims Data Analytics. J Artif Intell Mach Learn & Data Sci, 8(1), 3382-3390.
Venkata, S. B. (2026, March). HERA-QI: Vision Language Quality Inspection for Hearing Aid Hardware and Software. In 2026 9th International Conference on Intelligent Computing and Control Systems (ICICCS) (pp. 2000-2006). IEEE.
Venkata, S. B. (2025, December). Predictive infrastructure orchestration in azure using terraform and dynatrace for medical systems. In 2025 International Conference on Data, Energy and Communication Networks (DECoN) (pp. 1-6). IEEE.
Venkata Krishna Bharadwaj Parasaram, Satish Kumar Nalluri & Varun Teja Bathini, “Artificial Intelligence Driven Management Systems for Optimizing Efficiency in Smart Industrial Environments”, International Journal of Multidisciplinary Research and Modern Education, Volume 1, Issue 2, Page Number 489-514, 2015. https://doi.org/10.5281/zenodo.19634549
Venkata Krishna Bharadwaj Parasaram, Satish Kumar Nalluri & Varun Teja Bathini, “AI-Integrated Architectural Frameworks for Intelligent Production and Operational Control Systems”, International Journal of Multidisciplinary Research and Modern Education, Volume 1, Issue 2, Page Number 515-540, 2015. https://doi.org/10.5281/zenodo.19634601
SAP SE. (2025). SAP Student Lifecycle Management: Cloud Architecture and BTP Integration Guide 2025. SAP Press.
Siemens, G., & Long, P. (2011). Penetrating the fog: Analytics in learning and education. EDUCAUSE Review, 46(5), 30–40.
Satish Kumar Nalluri, Venkata Krishna Bharadwaj Parasaram & Varun Teja Bathini, “Machine Learning-Based Management Models for Scalable and Resilient Industrial Platforms”, International Journal of Engineering Research and Modern Education, Volume 1, Issue 1, Page Number 760-785, 2016. https://doi.org/10.5281/zenodo.19634396
UNESCO. (2025). Recommendation on the Ethics of Artificial Intelligence in Education — Implementation Review. United Nations Educational, Scientific and Cultural Organization.
Varun Teja Bathini, Satish Kumar Nalluri & Venkata Krishna Bharadwaj Parasaram, “Autonomous Management Systems Using Artificial Intelligence for High-Performance Industrial Automation”, International Journal of Scientific Research and Modern Education, Volume 2, Issue 2, Page Number 104-122, 2017. https://doi.org/10.5281/zenodo.19634468
Manne, V. T. (2026). Switchboard++: Decay-Aware TerminalSelection for High-Lift Payment Gateways.
Manne, V. T. (2026, January). Adaptive graph-based risk scoring for real-time instant payment systems. In 2026 Second International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS) (pp. 1-7). IEEE.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ramesh Iyer, Kavitha Sundaram (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.