TAMU Recommendation Engine


We loved the idea of providing recommendations to future datathon participants about workshops that they can attend based on their data science experience and interests. With data science being such a massive field, it can be difficult to decide on a starting point. This can be especially daunting for newcomers to the field. For more experienced users that are looking to expand their skills, it is helpful to be able to match ones level of experience to new and exciting topics.

What It Does

The webpage is designed to give TAMU datathon participants recommendations of workshops based on their experience, major, and interests. Once a user signs up, it will start recommending workshops they can attend.

How We Built it

React Framework with next.js front end and Flask Backend

We decided to use react framework for this project so we could not only perform the data analysis but so we could also integrate it into a smooth webpage that would create an enjoyable experience. Using next.js for the client-side we first take user input, POST to the Flask backend, perform analysis based upon the given user input, return the information to the server, and then fetch from the client-side to personalize the dashboard with the users specific information.

Challenges We Faced

Next.js was made to be serverless and run with Vercel, so we had to face the challenge of integrating a Flask server with a React frontend. This brought difficulties in communitcating between the server and the client. Once that worked, there were more difficulties in formatting the data so that it could be used with our Data analysis.

Accomplishments That We're Proud Of

We where able to give recommendations based on skills, experience, and major. We are also proud that we where able to make the log in process accessible and easy to read for all users.

What We Learned

We learned about integrating custom servers with React front ends and the benefits of it with difficulties as well. We learned about how browsers communicate with servers and how to get data from a client and use it for computational purposes.

What's Next For TAMU Recommendation Engine

Implement a webpage without having to log in with your credential. We would also like to put statistics on the users preference to be able to personally compare each user to others that are in the same field and that have the same interests. This would help to connect an individual to the greater pool of participants.

Built With

Share this project: