Cauldron Optimizer

Our Website's Layout
Cauldron 1's Potion Level Based on Given Data and the Next Week Based on Our Prediction Using XGBoost
All Cauldron's Potion Level Based on Given Data then the Next Week Based on Our Prediction Using XGBoost

Inspiration

We were inspired by the problem statement put forth by EOG, a gold sponsor of HackUTD 2025.

What it does

Our application compares real time potion withdrawals from numerous cauldrons with tickets (receipts) of the amount of potion withdrawn from each cauldron, and highlights any discrepancies.

How we built it

The frontend was built using React.js, TypeScript, HTML and CSS. The backend was built with Python and FastAPI.

Challenges we ran into

The algorithm that flags discrepancies generates many false positives, and the frontend lacks polish owing to the fact that it is the team's first time making a project with React. Lastly, we did not take time to carefully plan out before coding, and that led to team members' code being wasted because somebody else already implemented it.

Accomplishments that we're proud of

We built a functioning web application.

What we learned

We learned how to extract and send data via APIs, and we learned how to use React.js. We also learned about using predictive models.

What's next for Team Registration

Moving away from predetermined data and using real-time data, determining the best course of action regarding couriers who generate many flagged tickets, and revamping the graphical interface.