<![CDATA[This study aims to develop a data-driven adaptive learning model to personalize learning pathways for elementary school students. The model is designed to adjust learning materials, difficulty levels, and exercises to individual abilities, making the learning experience more relevant and effective. The study employs a Research and Development method with stages including needs analysis, design, implementation, and evaluation through experiments involving sixth-grade students. Data were collected through academic tests, observations, and analysis of interactions on a digital platform, then analyzed using both quantitative and qualitative approaches to assess the model’s effectiveness. The results show a significant improvement in the academic scores of students using the adaptive model, increasing from an average of 71,4 to 86,2, compared to the control group, which improved from 70,9 to 76,1. The model also enhances student engagement, motivation, and self-confidence, while providing teachers with detailed information about individual learning needs. The adaptive system is capable of adjusting learning pathways in real time, delivering instant feedback, and supporting timely interventions. These findings confirm that data-driven adaptive learning improves academic outcomes and the quality of learning experiences in a personalized, inclusive, and sustainable manner, supported by adequate infrastructure, teacher training, and data security policies.]]>
