Google's AI developers challenge to forecast the outcome of NCAA's tournaments



The NCAA's March Madness college basketball tournament is about to get more interesting, as Google teams up to host a developers' challenge on Kaggle, the world's largest online community of data scientists, tasking the participants to build and train machine learning models to forecast the games’ outcomes.

Google has set aside $100,000 in prizes for any computer scientist or group who could write the best AI software to predict the outcome of the NCAA's March Madness college basketball tournament.

While Kaggle has hosted such contests in the past, this year’s competition will be taking things to the next level with a new data set that contains every play-by-play moment in men’s and women’s NCAA Division I basketball since 2009.

Since 2009, a database of 40 million basketball plays have been recorded in the men's and women's NCAA Division I basketball games.

The data scientists will run the database through their neural networks, and it involves a log-loss approach that grades how well their predictions fare for all matchups that actually took place.

And because the competition is based on ML models, not basketball know-how, makes anyone’s game a win.

Also, the NCAA is migrating 80+ years of data across 24 sports to Google Cloud Platform (GCP), using Google tools to power analyses of teams and players, which will afford everyone a strategy for making their picks for the NCAA’s March Madness tournament.
Previous
Next Post »