• 

  Charles Oliveira vs. Islam Makhachev

• 

  Conor McGregor vs. Khabib Nurmagomedov

• 

  Tracy Cortez vs. Mackenzie Dern

• 

  Fighter statistics displayed in tables

Inspiration

We are both huge fans of the UFC and for the longest time we wanted to be able to accurately predict the outcome of UFC Fights based upon the statistical data that is available(and its correlation factor to the overall chances of winning). So, that's exactly what we did! With a user-friendly and easy-to-use UI, we have come up with a UFC Bout Predictor that looks into multiple data inputs and is highly accurate. We had a great time making this project and we would love to continue developing this in the future!

What it does

In the backend, we used multiple algorithms( randomforest, OLS, LR) to determine the factors that affect a fights outcome the most. Once we narrowed it down to 11 major contributing factors, we looked into datasets of individual fighters and gave them a score based on their individual corresponding statistics(which were multiplied by their correlation factor to produce the score).

Challenges we ran into

We had a hard time merging the back-end with the front-end due to differentation in syntaxing, and because Garman doesn't use comments. But, I am super thankful to have been a part of this project.

Built With

• beautifulsoup4
• pandas
• plotly
• python
• requests
• seaborn
• streamlit