Predicting Hockey Penalties with Azure Machine Learning

Using Regression Models and Automated Machine Learning to Predict High-Risk Games

This project is the results of a machine learning experiment that considers historical hockey games from 2001–2020 to build a regression model capable of predicting the number of penalty minutes that might be expected for a given NHL hockey game factoring in only the home team, the away team, and whether the game was a playoff game or regular season matchup.