AI-Driven Student Success: A Systematic Review of Retention and Academic Performance Prediction in Higher Education

Artificial Intelligence (AI) has emerged as a promising approach for addressing challenges related to student retention and academic performance in higher education. Despite the growing adoption of AI-based predictive systems, existing studies are fragmented across different methodologies, datasets, and educational contexts, making it difficult to obtain a comprehensive understanding of current developments and future research directions. This study aims to systematically review the application of AI techniques for student retention and performance prediction in universities.

A systematic literature review was conducted on studies published between 2020 and 2026. The review examined AI methodologies, predictive models, evaluation metrics, key predictive factors, application areas, implementation challenges, and emerging research opportunities. Relevant studies were identified, screened, and analysed to provide a comprehensive overview of the current state of research.

The findings indicate that AI-based predictive models consistently outperform traditional statistical approaches in identifying students at risk of academic failure or dropout. Machine learning and deep learning techniques, including Random Forest, Decision Trees, Support Vector Machines, Artificial Neural Networks, and Long Short-Term Memory models, demonstrated strong predictive performance across diverse educational datasets. The review further reveals that academic achievement, learning management system engagement, behavioural patterns, and socioeconomic factors are among the most influential predictors of student outcomes. However, challenges related to data privacy, algorithmic bias, model interpretability, and cross-institutional generalizability remain significant concerns.

The study concludes that future research should prioritize explainable and ethical AI frameworks while promoting human-centred implementation strategies to enhance decision-making and student success in higher education.