Programa especializado: Sports Performance Analytics

This course provides an introduction to using Python to analyze team performance in sports. Learners will discover a variety of techniques that can be used to represent sports data and how to extract narratives based on these analytical techniques. The main focus of the introduction will be on the use of regression analysis to analyze team and player performance data, using examples drawn from the National Football League (NFL), the National Basketball Association (NBA), the National Hockey League (NHL), the English Premier LEague (EPL, soccer) and the Indian Premier League (IPL, cricket).

This course does not simply explain methods and techniques, it enables the learner to apply them to sports datasets of interest so that they can generate their own results, rather than relying on the data processing performed by others. As a consequence the learning will be empowered to explore their own ideas about sports team performance, test them out using the data, and so become a producer of sports analytics rather than a consumer. While the course materials have been developed using Python, code has also been produced to derive all of the results in R, for those who prefer that environment.

The book Moneyball triggered a revolution in the analysis of performance statistics in professional sports, by showing that data analytics could be used to increase team winning percentage. This course shows how to program data using Python to test the claims that lie behind the Moneyball story, and to examine the evolution of Moneyball statistics since the book was published. The learner is led through the process of calculating baseball performance statistics from publicly available datasets. The course progresses from the analysis of on base percentage and slugging percentage to more advanced measures derived using the run expectancy matrix, such as wins above replacement (WAR). By the end of this course the learner will be able to use these statistics to conduct their own team and player analyses.

In this course the learner will be shown how to generate forecasts of game results in professional sports using Python. The main emphasis of the course is on teaching the method of logistic regression as a way of modeling game results, using data on team expenditures. The learner is taken through the process of modeling past results, and then using the model to forecast the outcome games not yet played. The course will show the learner how to evaluate the reliability of a model using data on betting odds. The analysis is applied first to the English Premier League, then the NBA and NHL. The course also provides an overview of the relationship between data analytics and gambling, its history and the social issues that arise in relation to sports betting, including the personal risks.

Sports analytics now include massive datasets from athletes and teams that quantify both training and competition efforts. Wearable technology devices are being worn by athletes everyday and provide considerable opportunities for an in-depth look at the stress and recovery of athletes across entire seasons. The capturing of these large datasets has led to new hypotheses and strategies regarding injury prevention as well as detailed feedback for athletes to try and optimize training and recovery.

This course is an introduction to wearable technology devices and their use in training and competition as part of the larger field of sport sciences. It includes an introduction to the physiological principles that are relevant to exercise training and sport performance and how wearable devices can be used to help characterize both training and performance. It includes access to some large sport team datasets and uses programming in python to explore concepts related to training, recovery and performance.