/sport_analysis_and_viz

In this project, we created an 'expected goals' metric to help us assess a team's performance rather than the actual number of goals scored. We merged this metric with the calculation of a team's offensive and defensive ratings, which are updated after every game, to create a classification model that predicts the outcome of future matches, as well as a regression model that predicts the score of future games Our models outperform existing traditional techniques and achieve similar accuracy to betting sites' models.

Primary LanguagePython

This repository is not active