Posted

Love ‘em or Hate ‘em Branch Rickey, of breaking the baseball color barrier with the Brooklyn Dodgers and Jackie Robinson fame, had a lifelong fascination with statistical analysis. In 1913 he hired someone to sit behind home plane and keep track of how many bases each player achieved for himself and his teammates. Michael Lewis’ best-selling 2003 book, Moneyball, made statistical analysis in sports famous and standard practice in Major League Baseball. Instead of assessing player performance by anecdote and intuition, the General Manager of the Oakland Athletics, Billy Beane, used an evidence based approach to tremendous success. What is the future of Big Data Analytics and Sports?

11th Annual MIT Sloan Sports Analytic Conference

There are conferences just for the study and implementation of analytics into sports. The Sloan Sports Analytics Conference is the granddaddy of sports conferences with some of the biggest names in sports attending or presenting: Commissioner of the NBA, Adam Silver, Owner of the Dallas Mavericks, Mark Cuban, GM of the Golden State Warriors, Bob Myers, players like Shane Battier and Sue Bird, and Nate Silver, Statistician and Founder of FiveThirtyEight.

Session titles include: Body Shots, Analyzing Shooting Styles in the NBA using 3D Body Pose Information, A Switching Dynamic Generalized Linear Model to Detect Abnormal Performance in MLB, Scraping and Analyzing NFL Data with R, one whole session just on SQL, Data Driven Storytelling and the Science of Sleep.

State of the Art Object Tracking Systems

In basketball multiple video cameras track the movements of every player on the court and the basketball 25 times per second. The sheer volume of the data has overwhelmed the analysis and no one has yet been able to show that tracking player movements can help the win-loss ratio.

“State of the art object tracking systems now produce spatio-temporal traces of player trajectories with high definition and high frequency, and this, in turn, has facilitated a variety of research efforts, across many disciplines, to extract insight from the trajectories,” say Joachim Gudmundsson and Michael Horton at the University of Sydney in Australia. Is a player open to receive a pass? Can one player be identified as putting pressure on other players around them? How can this be measured and modeled?

Network science is being applied to these trajectories. Each player is a node and a line is drawn between them as a ball travels from one to another. This has been more successful in sports research because a wide range of mathematical tools have already been developed for analyzing networks.

Technology Boosting Performance

The physiological components of sports are well studied. Optimizing the running style of a sprinter, the hydrodynamic properties of a swimsuit, controlling the heart rate of shooters in archery or a biathlon are well-along in their analysis. Wearables like arm bands and special shirts now measure vital signs during practice or even games. There is a sensor on a tennis racquet that stores information about shot power, ball impact location, number of strokes, spin, endurance, technique, consistency and rallies.

“But analytics tying those physiological models (e.g., “How do you optimize the torque a batter gets when swinging?”) to performance models (e.g., “What’s the potential increased value of this batter’s offensive contribution.”) haven’t been investigated that much, notes Joel Sokol, Associate Professor in the MS in Analytics program at Georgia Tech. Again, the need to turn data into more scores, more wins.

Genomics

Medical Futurist asks, “What if science might help in telling you what kind of sports you should try based on your genes? What if they tell you how you should change your work-out or your overall training in order to prevent injury? Or what kind of nutritional demands you have?” Collecting DNA through a simple blood test to improve performance, health and safety is already happening but there are still tremendous possibilities for greater impact on sports performance.

The big challenge in sports analytics is to use the data to gain a competitive advantage whether it is in real time during the game or to help in training, preparation or recruitment.

Speaking of recruitment, do you have an interest in hiring or a career in Big Data analytics? Contact Smith Hanley Associates Data Science and Analytics Executive Recruiter, Nihar Parikh, at nparikh@smithhanley.com or 313.589-7581.


Leave a Reply

Your email address will not be published. Required fields are marked *