Soccer Analytics with Machine Learning

Chapter 10. What’s Next for Soccer Analytics?

A Note for Early Release Readers

With Early Release ebooks, you get books in their earliest form—the author’s raw and unedited content as they write—so you can take advantage of these technologies long before the official release of these titles.

This will be the 10th chapter of the final book. Please note that the GitHub repo will be made active later on.

If you’d like to be actively involved in reviewing and commenting on this draft, please reach out to the editor at [e-mail].

By the final chapter of this book, the most important thing you have built is not a single model. It is a workflow for reasoning with data. Soccer gave us the setting, but the deeper achievement was learning how to move from a question to a usable analytical result: frame the task, gather data, clean it, explore it, engineer features, train models, evaluate them, and interpret them with care.

That workflow is the real conclusion of the book. Soccer gave us a rich and intuitive environment in which to learn, but the larger lesson is about how to reason inside a complex, uncertain system. Matches are noisy. Performance is contextual. Predictions are probabilistic. And useful analysis depends as much on judgment and representation as it does on algorithms.

This final chapter therefore has two jobs. First, it brings the main ideas of the book back together, so the overall arc is clear. Second, it points forward. If you want to continue in soccer analytics, ...