Predictive Analytics and AI in Education: A Systematic Literature Review on Identifying and Supporting At-Risk Students
Bibliographic record
Abstract
This research presents a comprehensive systematic literature review (SLR) examining the integration of predictive Artificial Intelligence (AI) technologies in educational settings. As institutions worldwide pursue personalized, inclusive, and data-driven learning environments, AI-based predictive analytics and Learning Analytics (LA) offer transformative potential. These tools support early identification of at-risk students, personalized learning pathways, and data-informed academic and administrative decisions. However, the adoption of predictive AI in education also introduces ethical, technical, and operational challenges. The study highlights critical concerns such as data privacy, algorithmic fairness, explainability, and stakeholder involvement, all of which impact implementation and trust in educational AI systems. The opacity of machine learning models—the “black box” issue—further complicates efforts toward transparency and accountability. By analyzing empirical studies, real-world university case studies, and systematic reviews, this paper explores both the benefits and limitations of predictive analytics in education. It emphasizes key outcomes such as individualized learning, enhanced student engagement, and administrative efficiency while also addressing bias propagation, ethical dilemmas, and stakeholder exclusion. The review concludes with strategic recommendations for the ethical, inclusive, and transparent implementation of predictive AI in education. It calls for ongoing evaluation and innovation that prioritizes fairness, stakeholder engagement, and the development of explainable AI (XAI) models. Keywords: Predictive Analytics, Artificial Intelligence in Education (AIEd), Learning Analytics (LA), At-Risk Students, Early Intervention, Educational Data Mining (EDM), Explainable AI (XAI)
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.015 | 0.085 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.004 |
| Bibliometrics | 0.012 | 0.010 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".