Applied data science in college basketball


Revenge of the Nerds was so 1980s. Now it's a new world order: math geeks and athletes are working together.

I'm not talking just about what happens when data nerds observe, analyze, and predict sports outcomes -- as they do in March Madness with their "bracketology". That's compelling, but your ability to predict an outcome is nothing when compared with the ability to influence the outcome.

That's what my friend Drew Cannon is doing for the Butler Bulldogs, and even Sports Illustrated has noticed the impact.

I first mentioned Drew in a blog 3 years ago, when his work as a summer intern for a basketball scouting publication earned him recognition in a New York Times article.

Today, he's on the bench as an assistant coach, diligently recording every aspect of the game that can be counted and measured. He then compiles the data, analyzes it, and uses it to inform the head coach via a system of "rules": for example, which players work well together in which situations. When the rules are followed, there's a better outcome. From the Sports Illustrated article:

"I love it when Drew [reminds]a guy who coached in two national championship games [of these rules]," Butler assistant Michael Lewis said. "He'll say, 'When we played by the rules, we were plus 5. When we didn't we were minus 3.' I love it, for a 22-year old kid to have the guts to say it."

Guts? Yes, I believe it. But when you've got the data and a solid analysis, it's a lot easier to muster your nerve.


About Author

Chris Hemedinger

Senior Manager, SAS Online Communities

+Chris Hemedinger is the manager of SAS Online Communities. Since 1993, Chris has worked for SAS as an author, a software developer, an R&D manager and a consultant. Inexplicably, Chris is still coasting on the limited fame he earned as an author of SAS For Dummies.  He also hosts the SAS Tech Talk webcasts each year from SAS Global Forum, connecting viewers with smart people from SAS R&D and the impressive work that they do.


  1. What a cool example! While in grad school, my project was to analyze data for the men's national volleyball team and suggest what skills were the most important to focus on in practice. For example, is it better to have a killer jump serve that is more prone to errors, or a highly consistent float serve that isn't as difficult to pass? Or is it better to have a giant in the back row who can hit behind the 10-foot line, or a quick, speed little guy who plays amazing defense? I can't reveal my secret discoveries, but I would like to think my suggestions had something to do with their gold medal in China :) I love statistics in sports...

  2. Pingback: Video: Transforming data into a corporate asset - SAS Voices

Leave A Reply

Back to Top