Rice Datathon 2024 Chevron Challenge

Inspiration

We really wanted to tackle a topic where we didn't have a lot of experience as a whole. Also, being a team with a Finance major and a Math-Econ major, we wanted to do a track that would really be a challenge, and this track proved very difficult and satisfying to attempt.

What it does

We predicted Oil Peak Rate through a random forest regression model.

How we built it

We built our model using scikit-learn libraries and we pre-processed our data using a multitude of techniques and many python libraries.

Challenges we ran into

We were having a lot of trouble properly preprocessing data and this is what took the vast majority of our weekend.

Accomplishments that we're proud of

We are proud that we were able to get an RMSE of 81 with our final random forest regression model.

What we learned

We learned a lot about data wrangling and data exploration tools, as well as how to really grind out a challenge that spans multiple days. Definitely was a rewarding experience and would totally do again.