Inspiration
My friend Meet and I are both underclassmen majoring in Computer Science. We both have very different interests within the field, and are often confused about the courses we should opt for in the future. We yearned for an application that could help us solve our dilemmas about course selection. Hence, came the idea of Scarlet Selector.
What it does and How it was Made
Scarlet Selector has two modes of viewing, anonymously and through your Rutgers NetID. When viewing without logging in, all you have to do is list your major, your GPA, your year of standing, and your interests. With these entries, the beautiful front-end design, made by Tanay Desai on React, connects to local Flask server created by our backend engineer, Naman Shah. All this data is then sent to a large language model, which is fine tuned to fit over two thousand Rutgers courses by department and school. Made by our Machine Learning Engineer, Archit Bansal, the model then recommends 5 courses per all these instructions. If the user wishes to see more information on these courses, they can click the hover board, and that would lead them to Selenium, which lets them access the survey ratings for these professors.
And the second case, what if you wish to view your own personal classes. This is where Scarlet Selector really shines, as the user can log onto your Rutgers NetID and access the courses you've previously taken and the grade you have gotten in them.
What's next for Scarlet Selector?
We wish for Scarlet Selector to take on a much more advisory position. While we had plans of implementing a Scarlet Box, a chatbot that communicates with you over your interests, majors and minors plan. Next, we want Scarlet Box to tell the users what's the best time to take a course based on the RateMyProfessor API.
Log in or sign up for Devpost to join the conversation.