Sleuth

Inspiration

Frustrated with the lack of accessibility and exposure of clubs and organizations at UCLA, we decided to create the simplest solution to help you look for clubs Bruins actually care about – not the hundreds of extraneous clubs that don’t cater to their interests.

What it does

Sleuth introduces a questionnaire that gives the user an open floor to speak about any interests. A one-word response with machine learning; long lines highlighting their love for entrepreneurship – Sleuth utilizes a machine-learning algorithm trained through scraped UCLA data to create a sophisticated match score, and ranks the top 5 most suitable clubs.

How we built it

CSS, Python, HTML, JS, united with Flask

Challenges we ran into

It was incredibly difficult incorporating our front-end applications with our back-end applications. We attempted to use Framer to export an HTML file to integrate with a Typeform API, but we realized this was incredibly hard and out of our budget and timeframe to make it feasible.

Accomplishments that we're proud of

Building a workable prototype and participating in our first hackathon!

What we learned

We learned how to webscrape and iterate under a critical, time–sensitive environment.

What's next for Sleuth

We hope to extend beyond clubs and organizations and into class planners, 4-year plans, and an accessible searchbase for internal opportunities at UCLA.