Date of Award

5-2024

Degree Type

Thesis

Degree Name

Honors Thesis

Department

Mathematics

First Advisor

Mohammad Shaha A. Patwary

Second Advisor

Rasitha Jayesekere

Abstract

The advent of sports analytics has ignited a fervor across all sporting disciplines, particularly soccer, where clubs are sprinting to harness vast data reserves to elevate team performance, spearhead effective marketing endeavors, and bolster financial gains crucial for club expansion. Much like Billy Beane's transformative "Moneyball" approach, soccer clubs are in pursuit of innovative strategies to transcend financial limitations and achieve triumph. In soccer, where goals are scarce commodities, heightened offensive efficacy becomes imperative. Presently, one metric stands out as pivotal in gauging a team's goal-scoring success: expected goals (xG). This metric quantifies the likelihood of a given shot or opportunity culminating in a goal, making it a linchpin in a team's offensive strategy. Maximizing expected goals becomes paramount for teams aiming to capitalize on limited scoring opportunities during matches. Crucially, the first step in reshaping tactical approaches hinges on identifying the most influential variables in predicting expected goals. To this end, this study employs an array of machine learning methodologies, including Ridge, Lasso, Elastic Net, and Group Lasso models. The objective is to unveil the key predictor variables that significantly impact team (offensive) performance, often delineating the thin line between championship glory and defeat. With the aim of predicting xG, this research also incorporates modified bootstrap techniques to compute prediction intervals for the regularized machine learning models. By delving into the intricate fabric of soccer analytics, this study seeks to empower clubs with actionable insights, fostering a new era of strategy and competitive edge on the field.

Download

Included in

Mathematics Commons

Share

COinS