Expected Goals in Soccer

Logistic Regression
Feature Engineering
Under Sampling
An Introduction to Expected Goals Using Soccer
Authors
Affiliation

Colman Kim

West Point

Andrew Lee

West Point

Published

May 19, 2025

Module

This module introduces students to Logistic Regression, Feature Engineering, and Undersampling using a soccer-specific Expected Goals Model. We explain how to create a logistic regression model, using data gathered by Statsbomb from the 2022 World Cup.

This module is available on the ISLE platform Expected Goals in Soccer Module