Soccer Analytics with Machine Learning: Learning Predictive Modeling Techniques with Sports Data

Struggling to grasp machine learning concepts or unsure how to apply them in the real world? This book aims to change that by using the world's most popular game--soccer--to illuminate key concepts in predictive modeling and data science. You'll develop a solid foundation in machine learning through engaging examples that bridge academic principles with practical applications.

Written by experts in both machine learning and sports analytics, this practical Python-focused guide introduces fundamental data science techniques using real soccer data. Ideal for students, analysts, and soccer fans alike, it offers instructions on models and techniques such as logistic regression, random forests, deep learning, simulations, and feature engineering. But instead of memorizing algorithms, you'll learn by building predictive models to analyze match outcomes, test betting strategies, run simulated game scenarios, and more.

• Understand machine learning concepts by working with real sports data
• Develop, refine, and evaluate machine learning models, using Python for data analysis
• Carry out detailed analyses and research on soccer game predictions and betting strategies to surface valuable insights
• Apply the skills you learn to predictive modeling scenarios in other industries

Haipeng Gao is a data science and machine learning expert with extensive industry experience building and optimizing large-scale machine learning systems at leading technology companies, including LinkedIn, TikTok, and PayPal. He holds a PhD in Statistics and Operations Research from the University of North Carolina at Chapel Hill, has taught statistics and probability at UNC Chapel Hill and San Jose State University, and holds multiple AI/ML patents granted by the U.S. Patent and Trademark Office.

Ari Joury is a data scientist and entrepreneur working at the intersection of machine learning, causal inference, and applied analytics. He is the founder and CEO of Wangari Global, where he builds AI systems for decision support in finance, insurance, and sustainability, with a focus on interpretable models and real-world impact. Trained originally as a theoretical particle physicist, he later transitioned into applied data science and quantitative modeling. Ari holds a PhD in Physics and an MBA.

Weining Shen is an associate professor of statistics at the University of California, Irvine. His research focuses on machine learning, Bayesian statistics, sports analytics, and large language models. Dr. Shen has published more than 70 papers in leading statistics journals and at premier machine learning conferences. He earned his PhD in Statistics from North Carolina State University.

Guanyu Hu is an associate professor at Michigan State University. His research focuses on spatial statistics, Bayesian nonparametric methods, and sports analytics. He has led multiple NSF-funded projects and published more than 50 papers in leading statistics journals and machine learning conferences. Dr. Hu serves as an associate editor for several prominent journals, was chair of the American Statistical Association's Statistics in Sports Section in 2024, and is one of the organizers of the American Soccer Insights Summit. He received his PhD in Statistics from Florida State University.