Background Information
Supporting every student towards successful completion of their studies is a core ambition of TU/e education. Within the Biomedical Engineering bachelor's program, students face an exciting but challenging mix of foundational courses in mathematics, engineering, and experimental skills. These early courses, such as Calculus and Skills Experience, are crucial for long‑term success and many students can benefit from additional guidance as they adapt to the pace and expectations of university education. To support all students achieving their success while maintaining a sustainable workload for teachers, it is essential to fully understand which factors most strongly contribute to students’ difficulties and success. This would help identify when and what type of support would be most effective. At present, the department lacks systematic and quantitative insight into these topics.
At the same time, TU e holds a growing amount of educational data that is ethically approved for learning analytics. When used responsibly and in anonymized form, this data offers opportunities to better understand student learning trajectories to guide evidence‑based improvements to the courses that help all students progress with confidence.
This pilot responds to the need for evidence based student support by exploring how learning analytics can be used to improve the quality of student support towards success and optimize early guidance within the Biomedical Engineering curriculum.
Aim of the project
The aim of this project is to develop a learning analytics model that identifies key factors that contribute to student success in the Biomedical Engineering bachelor and translate these insights into actionable support strategies for all students. By analyzing historical, anonymized student data such as early performance indicators, the project seeks to pinpoint which parts of the curriculum have the greatest influence on learning progression and where students may benefit most from additional support.
The project does not aim to label or single out individual students in ongoing courses. Instead, it focuses on identifying patterns from historical data and using these insights to inform teachers and students about critical moments in the learning process. This enables earlier and more targeted support, such as additional coaching, peer support, or adapted learning resources.
For teachers, the project aims to provide concrete insights into which courses and learning activities require attention and where interventions are likely to have the greatest impact. This supports more efficient use of time and resources, without increasing overall workload.
For students, the project aims to strengthen self directed learning by increasing awareness of learning strategies, progress, and expectations, in addition to enhance student access to early support opportunities.
At an institutional level, the project aims to establish a responsible and scalable approach to using learning analytics for improving student success.
For more information, please contact:
