Intelligent Tutoring Systems (ITS) are widely used to manage, deliver, and evaluate educational content; however, most lack adaptive capabilities to meet individual learner needs. This study integrates three key components—student activity tracking, performance prediction, and data visualization—to enable early identification of at-risk learners and support targeted interventions. Leveraging deep learning techniques enhances prediction accuracy, demonstrating the potential of advanced analytics to improve instructional decision-making, personalized feedback, and overall learning outcomes.
Paper
The full text of this publication is not hosted on 44B due to licensing.
Read it at OpenAlex