The Role of Adaptive Learning Technologies in Personalized Education

Abstract

As educational systems strive to move beyond "one-size-fits-all" pedagogical models, Adaptive Learning Technologies (ALTs) powered by Artificial Intelligence (AI) have emerged as a critical solution for personalization. This paper presents a systematic literature review examining the efficacy of ALTs in enhancing learner engagement, academic performance, and equity. Analyzing peer-reviewed studies published between 2019 and 2025, the review focuses on the transition from rule-based systems to advanced Machine Learning (ML) algorithms, specifically contrasting Bayesian Knowledge Tracing (BKT) with Deep Knowledge Tracing (DKT) and Transformer-based models. Key findings indicate that ALTs yield a significant positive effect on cognitive learning outcomes and bolster student motivation (Chaudhry et al., 2025; Martinez & Anderson, 2024). However, the study identifies critical barriers, including the "cold start" problem, algorithmic bias in minority representations, and the "Black Box" opacity of neural networks (Baker & Hawn, 2021; Heaven, 2024). The paper concludes that while ALTs are potent tools for democratization, their sustainable success is contingent upon the integration of Explainable AI (XAI) frameworks and robust fairness-aware algorithms (Liu et al., 2024).