Predicting March Madness in Tableau

Data

Predicting March Madness in Tableau

I know, I know. The idea of actually predicting March Madness with any accuracy is an exercise in futility, although that may partially explain why the tournament so fully captures the attention of so both the casual enthusiast and the diehard fan of the game alike. After Selection Sunday, the night the committee releases the bracket to the general public, fans are off to the races filling in brackets, anticipating more hyped matchups and over-analyzing each region to death. Since it’s getting close to that time of year, I’ve put together a dashboard to aid in each of these time-honored traditions.

Using Robert Rouse’s Import.io Web Data Connector, the data was pulled straight from Kenneth Pomeroy’s website detailing each of the 351 Division 1 programs in college basketball. Just choose a couple of teams and whether there is a home court advantage to see how the game might shake out!

While these may not line up exactly with KenPom’s predictions (his system uses a proprietary formula, you can read more about it here), the dashboard does allow you to pit any two teams against each other and generate a prediction great for solving useless arguments about who would win between x and y.

For example, Joe Lunardi currently has my Hoosiers at a six seed in the Midwest region (all seeds/stats as of 2/2/16), I can check on how they may fare against the eleventh-seeded Valparaiso. While home court advantage has a significant impact for Ken’s predictions, Joe has this game occurring in Spokane, Washington, which should be a fairly neutral court being on the other side of the country from both Indiana-based schools.

With these parameters selected, we can see that such a game would be very interesting. Valpo has the slight edge with their stifling, first-ranked defense (allowing a mere eighty-nine points per hundred possessions), so Tom Crean and company will have their hands full. But don’t count out the Candy Stripes just yet! Valparaiso has had awful luck this year, a metric which measures how a team has fared in close games throughout the season. If it really comes down to it, the Hoosiers may find a last minute way to make it through to the next round. For a fictitious matchup that will likely not even happen, I’m already excited for March!

By the way, if you’d like to see predictions on the go, I also put together a smaller version for mobile use. Check it out!

More About the Author

Jimmy Steinmetz

Solutions Lead
Debriefing My Trip to Dataiku HQ Recently, David Siegel, Rachel Kurtz and I spent the day with the team over at Dataiku HQ in New York to learn about the platform and ...
A Quick Exasol Script for Building Python UDFs A client recently had a challenge wanting to use Exasol’s User-Defined Functions with a Python script, but they were having a hard time ...

See more from this author →

Subscribe to our newsletter

  • I understand that InterWorks will use the data provided for the purpose of communication and the administration my request. InterWorks will never disclose or sell any personal data except where required to do so by law. Finally, I understand that future communications related topics and events may be sent from InterWorks, but I can opt-out at any time.
  • This field is for validation purposes and should be left unchanged.

InterWorks uses cookies to allow us to better understand how the site is used. By continuing to use this site, you consent to this policy. Review Policy OK