HackStack

Project Info

BeliMatch

Devpost

This project did not submit a demo video on Devpost.

Inspiration

Food is a universal language. People bond and share memories over food. As teammates, we bonded over running to Codegen's free boba giveaways and rating the new DoorDash business model of homecooked meals. Since food was able to bring us together, we thought, why isn't there a better way to learn about people's food preferences, and even meet people based off of food preferences. All of us have been sharing our food reviews on apps like Beli, and we wanted to leverage AI technologies and other innovations to make it easier for others to meet based off of their tastes in food.

What it does

BeliMatch, like DataMatch, helps match you to your most compatible partner through your food preferences and suggests a first date location for both of you to enjoy a great time. After you submit the introduction form, we gather information like your top 25 restaurants on Beli, and we use this to run a matching between what you're looking for, your food preferences, and what others are looking for. At the end of the matching, we send emails to each user with personalized recommendations and their new friends / date matches.

How we built it

BeliMatch uses React framework with a Firebase backend, and our unique matching algorithm that leverages AI to generate the best matches.

Challenges we ran into

Creating the pipeline to get the relevant features from a user's Beli or Yelp profile through web scraping and collecting detailed restaurant data was more challenging than anticipated since this was an unexpected technology hurdle we had to overcome. The matching also ended up being more difficult than anticipated due to rules around school matching and preferences that users inputted into the app.

Accomplishments we're proud of

Being able to actually provide matches that could potentially lead to friendships and more! We went around Treehacks getting users to sign up for our service and many were actually very excited about the idea and filled out our form.

What we learned

From a technical skills perspective, we learned how to use AI in matching algorithms and use Twilio to send out emails. Additionally, we learned some soft skills when going around pitching our idea and learned how to make people the most excited about it.

What's next

BeliMatch will run our first batch of matchings at the end of TreeHacks, after receiving overwhelming interest from fellow hackers. Beyond that, we hope that BeliMatch will take off into a platform that helps connect people through our shared universal language -- food.

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • CSSIn code
  • FirebaseIn code
  • HTMLIn code
  • JavaScriptIn code
  • PythonIn code
  • ReactIn code
  • VercelClaimed

6 of 7 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

37 KB

Source files

18

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars