About the Author

DataField.Dev

This textbook was drafted with AI assistance and is published by DataField.Dev as a free, open educational resource. It is not the work of a team of former quantitative traders, academic statisticians, or professional bettors, and it has not been formally peer reviewed or classroom-tested. It draws instead on the published academic literature, the openly shared work of the sports analytics community, and the open-source Python ecosystem, all of which are credited in the text.

The book is built on a conviction that rigorous analytical thinking can transform how we understand and engage with sports, and on a belief that sports betting, properly approached, sits at one of the most intellectually rich intersections in applied mathematics. It demands probability theory, statistics, machine learning, optimization, behavioral economics, domain expertise, and psychological discipline --- all operating simultaneously under genuine financial stakes. Few other domains offer this combination of analytical depth and immediate, measurable feedback.

The genesis of this textbook was a recognition that while excellent resources existed for individual components --- probability theory, machine learning, sports analytics, and risk management each have their own literatures --- no single resource integrated these disciplines into a coherent framework specifically designed for the quantitative sports bettor. Students and practitioners were forced to assemble their education piecemeal, translating concepts from finance, statistics, and computer science into the betting context on their own. This textbook aims to bridge that gap.

The book's editorial philosophy is to prioritize clarity over complexity, practical applicability over theoretical purity, and honest assessment of limitations over overconfident claims. Where the evidence is uncertain, we say so. Where common practices are flawed, we explain why. The models and code in this book are teaching examples: before relying on any of them with real money, test them yourself on data you trust.

We believe that the field advances fastest when knowledge is shared openly and subjected to scrutiny, and that applies to this book too. The analyses and opinions expressed here are not endorsed by any sportsbook, betting syndicate, or gambling operator.

We welcome correspondence from readers, instructors, researchers, and practitioners. Corrections, suggestions, and constructive criticism improve future editions and are gratefully received; you can reach DataField.Dev through datafield.dev/about.html.

DataField.Dev