KDnuggets Home » News » 2014 » Feb » News, Features » Kaggle March Machine Learning Mania ( 14:n04 )

Kaggle March Machine Learning Mania

Can you turn 20 years of historical data into predictions for 2014 NCAA College Basketball Tournament, aka March Madness? Enter this Intel-sponsored tournament - predictions due Mar 19.

March Machine Learning Mania March Machine Learning Mania

Each year, millions of people in the US fill out a bracket to predict the outcome of the NCAA men's college basketball tournament that starts in March (aka "March Madness"). While the odds of creating a perfect bracket are astronomical, these odds are made better by the growing amount of data collected throughout the season, including player statistics, tournament seeds, geographical factors and social media. How well can machine learning and statistical techniques improve the forecast?

Kaggle has assembled the basic elements necessary to get started with tournament prediction. The provided data covers nearly two decades of historical games, but you're also encouraged to use data from external sources. To help turn all of that information into useful insight, Intel is making its big data technologies more affordable, available, and easier to use for everything from helping develop new scientific discoveries and business models to gaining the upper hand on good-natured predictions of sporting events.

In stage one of this two-stage competition, participants will build and test their models against the previous five tournaments. In the second stage, participants will predict the outcome of the 2014 tournament. You don't need to participate in the first stage to enter the second, but the first stage exists to incentivize model building and provide a means to score predictions.

The real competition is forecasting the 2014 results, for which you'll predict winning percentages for the likelihood of each possible matchup, not just a traditional bracket.

Intel will present the team with the most accurate predictions a $15,000 cash prize.

Get started today - predictions are due by Wednesday, March 19, 2014.

To learn more and participate, visit www.kaggle.com/c/march-machine-learning-mania.