Diversity - MajorMentor

Inspiration

Our inspiration for creating this project stemmed from our personal experiences as university students. We understand the challenges of finding the right university in Canada, a process that typically requires considerable time and effort. Recognizing this, we envisioned a streamlined, single-platform solution that simplifies this journey for students nationwide. Our goal was to transform the often complex and time-consuming task of university selection into an efficient and user-friendly experience, reflecting our own desires for a more accessible higher education landscape.

What it does

Our project selects the most compatible university program for the user, then the user can choose to find the best university location relative to them, and finally select the most cost-efficient choice.

How we built it

We first had to build a personality quiz and relate it to the popular majors in Canada, this meant we were mapping to over 25 majors! Then we took into account locations, meaning user preference was considered, and the cities and provinces. Then budget and fees were considered by using an online tuition calculator that we interacted with through the PlayWright API. We then finally made a recursive model that allows the user to backtrack and change preferences in order to find the perfect fit

Challenges we ran into

One of the biggest challenges we ran into was trying to use selenium for our web interaction. As we are not that experienced in JavaScript and WebDev, this was difficult to use. Thanks to the help from Arun, a mentor, we switched to the PlayWright API which allowed us to complete the project within the deadline. Another problem we ran into was that we wanted to use a custom GPT bot for data set creation. Turns out GPT4.0 has a limited number of queries, so we had to get creative with our massive data set creation. We used a combination of both Python text processing, as well as GPT3.5, allowing us to create a dataset that was over a thousand lines of text to fit our needs!

Accomplishments that we're proud of

We are very proud of the iterative development approach we took to our project, as we started off with a basic function that eventually transformed into a complex recursive function. We are also proud of the amount of exception handling we used in our code, as it made it easy to debug. Another thing we are proud of is reacting on the fly when the custom GPT method for data set creation was not available in the middle of the night. We were able to solve the issue, and while it took a while, the rest of the development was not stopped because of this hurdle. Using a web Interaction API was also a big accomplishment, as now we are able to use this to much more use in the future

What we learned

We learned a lot of things so maybe it is best said in a list (ahaha) automated web tools iterative development integration of AI to format needed data very readable code frequent error handling to help debug NOT TO OVERLY DEPEND ON CHAT GPT FOR ANYTHING PlayWright API Selenium API A lot of Patience Power of Redbull

What's next for Diversity - MajorMentor

We're thrilled with the prototype of MajorMentor developed in HackedBETA and are eager to enhance it further. Our next steps include introducing a GUI for an enriched user experience, integrating comprehensive data on each major for more informed decision-making, and establishing a feedback mechanism. This will not only refine the user interface but also continuously improve the algorithm based on user input, ensuring that MajorMentor remains a dynamic and user-centric tool for navigating higher education choices.