Predictive Model to Predict NCAA March Madness Results

Erick McCollum | 09 Apr 2020

DISCLAIMER: The opinions expressed on this website are solely my own, and they are not associated with my employer, another person, or another organization in any way. All information on this website is provided "as is", without guarantee or warranty of any kind. Read the full disclaimer here.

I created three different predictive models with the objective of predicting NCAA March Madness tournament results. The three model types which were created are as follows:

  1. Random Forest
  2. Neural Network
  3. Stochastic Gradient Boosting

When comparing the performance of the three models, I found that the Stochastic Gradient Boosting model performed the best on my test sample data set.

For more details, please see the full project in my GitHub repository using the “View on GitHub” button below.

Acknowledgements

The data used for this analysis was obtained from Kaggle.com at the following location: