Abstract
Ensuring that students graduate on time (GOT) is a major hurdle for many universities, with over 80% GOT rates remaining elusive. Numerous research efforts, using statistical and machine learning approaches, have aimed to identify factors impacting timely graduation. Despite this, a comprehensive visualization of students' GOT trajectories has been a missing piece. This study addresses this gap by developing a predictive model that visually maps students' paths towards GOT. By projecting multifaceted academic data onto 2D planes, the model achieves impressive prediction accuracy ranging from 78.32% to 97.06%. This new tool empowers lecturers and the university's management to quickly identify students at risk of falling off track so that more precise preventive measures could be implemented to help these students achieve GOT.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
