Study experience estimation is a challenging task, as it must take into account different factors. At the same time, the estimation should be data-driven. Therefore, suitable data logging and gathering is relevant. In this challenge, the team should be aiming to enhance learning outcomes by leveraging data-driven insights to personalise study strategies for students. By utilizing machine learning, participants should develop ideas for tools that identify effective study habits and areas for improvement, fostering individualized learning experiences. This initiative not only equips students with actionable insights to optimize their academic performance but also promotes collaboration among tech and education professionals while addressing diverse learning needs in a rapidly evolving educational landscape.
The direction for the challenge ideas, which could be converted into multiple final thesis or individual project topics is the following:
- Prediction of student engagement in the study process, based on the course logs.
- Extended student action logging for more accurate student portfolio estimation.
- Student competency portfolio estimation, based on his or her textual CV description.
- Study program quality estimation, estimating the similarity between the study program content and market demand.
Regarding more details on the challenge and topics contact Simona Ramanauskaitė, VILNIUS TECH.