[UW Data Science Club x HFF] ParcoursLab: A Human-Centered Approach To Course Recommendations

ParcoursLab is an academic co-pilot that saves students and academic advisors time by building a course plan that respects degree requirements and pre-reqs while also taking into account your goal, desired skills, extracurricular interests, and crowd-sourced student ratings.

We use AI to automate the manual bookkeeping of reading through dozens of course descriptions and checking prereqs/eligiblity. However, despite this, the platform aims to be transparent, human-centered, and hallucination-free by retrieving course skills from a human-curated skills database (ESCO), providing you with justifications for each of its selection, and allowing you to update your plan conversationally.

In the linked demo, the student picks “Computer Science” as their major and “bioinformatics” as their goal. They also mention their interest in Music and Art. Our platform fetches your degree requirements and lays out your required courses (e.g. algorithms, operating systems) using ASAP/ALAP scheduling. Your goal is used to derive a set of desired skills (e.g. biochemistry, machine learning), matched against the ESCO database, which in turn guides a search for the ideal electives. We perform course recommendation using an LLM on a UWaterloo dataset deterministically distilled based on prereqs and augmented with student ratings. We also find you school clubs that match your major, goal, and extracurricular interests (e.g. Waterloo iGEM, Visual Arts club).

Courses can be dragged around, and prereqs are enforced. You can chat to replace courses. Adding a desired skill manually will add a course to your schedule that fulfils that skill. Lastly, the user can generate a printable AI summary that they can take to a meeting with an academic advisor for final human guidance.