It’s registration day. A student with a clear plan logs in to enroll in a mandatory course. They hit a familiar roadblock: it’s full. A waitlist forms. The student scrambles to rebuild a schedule, uncertainty rises, and the overall experience suffers.
When course demand and capacity don’t align, students face delays, and professors and administrators are pushed into complex forecasting, last-minute re-alignment, and added pressure.
The Faculty of Health Sciences is collaborating with Information Technology to address this issue by leveraging Machine Learning AI to forecast demand in advance. This approach enables teams to more effectively manage waitlists and plan course capacities, be using historical data and faculty trends to enhance decision-making confidence.
Why full-picture forecasting matters
Today, faculties often rely on manual estimates and local knowledge to plan registrations across semesters. But with thousands of students and countless schedule variations, it’s hard to predict the student journey with accuracy.
This initiative supports course planning with Machine Learning in a smarter way. Think of it like your music app, it learns from patterns and helps predict what you’ll want to listen to next. For the Faculty of Health Sciences, this is akin to leveraging thousands of registrations patterns to anticipate demand, optimize scheduling, and ensure that course offerings align with actual academic needs.
“Machine Learning in course planning is helping us see patterns we may miss while conducting manual analysis to better anticipate for the future.”
Meyssa Smirani
— Intermediate software developer
For course planning, it draws on nine information points across student profiles, faculty behaviours, and program context. It learns from historical patterns to anticipate future demand, and because it was built with Faculty partners, it reflects real academic workflows and the drivers that matter most.
The result: evidence-based, forward-looking signals that clarify course demand. Students get more reliable pathways to required courses with fewer registration roadblocks. Administrators gain earlier visibility which helps meet business requirements while reducing manual work.
By the end of this summer, the team plans to deliver a tool that brings clearer, earlier insights into course demand and can support Faculty planning for Fall 2027. Built as a repeatable approach, it is a solution that can scale to other faculties. Modernized course planning is a step toward a more effective, efficient, user-centric University with fewer bottlenecks for students, less reactive rework for staff, and faster, evidence-based decisions.
This research was aimed at shedding light on some significant inequalities. The data needed to be presented in a way that was straightforward and readily usable. With the collaboration of the Information Technology team, a clear and interactive dashboard was created as a tool to support informed decision-making.