Predicting the Score of the Chiefs vs the 49ers in Super Bowl LIV

Go Back to Home Page

I worked on a project to forecast the score of the super bowl using machine learning.

We built a linear regression model, a random forest model, and an XG Boost model to peform prediction running several scenarios with different assumptions. We delivered a presentation of our prediction methodology to an auditorium at the Paul Merage School of Business.

Our final model combined all of the previos models to give a score of 28-26 for the Chiefs which was off by 9 points from the actual score.

All the models were given equal weight to generate the final prediction. This method of ensemble modeling is championed by many skilled foreacasters.