Turning data into NCAA March Madness insights
Source: Turning data into NCAA March Madness insights from Google Cloud
Whether we’re collecting it, storing it, analyzing it, or just trying to make sense of it all, nearly all organizations wrangle with data. And this is particularly true for an organization like the NCAA®, with more than 80 years worth of data on everything from student-athlete performance to March Madness® tournament results.
Last year, we teamed up with the NCAA to help them bring together their wealth of historical data so they could better support students and schools, as well as delight fans. During the 2018 March Madness tournament, we used data analytics on Google Cloud to help us better understand the game, and build some fun predictions for what might happen. We turned these real time predictions in TV commercials during the Final Four—and we weren’t far off the mark!
In connection with this year’s March Madness tournament, we’re extending our NCAA campaign to developers everywhere with training that enables anyone with an interest in basketball and data analytics to dive in. More and more developers want to use Google Cloud, and we are ready to meet that demand. (In fact, a recent study by Indeed found that Google Cloud skills are the fastest cloud skills growing in demand.)
We’ve published a new series of Qwiklabs training to teach you how to use BigQuery to analyze NCAA basketball data with SQL and build a machine learning model to make your own predictions. At Google Cloud Next on April 9-11 (right after the Final Four), we’ll be hosting two bootcamps (Sunday and Monday) that use NCAA data to show you how to build a data science environment covering ingest, exploration, training, evaluation, deployment, and prediction. We’re co-hosting a predictive modeling competition with Kaggle that lets data scientists show their chops (and compete to win $10,000!). And we’ve published a technical blog post and a whitepaper to give you a deeper look under the hood.
We’re also demonstrating our platform’s accessibility and ease of use by recruiting 30 college students from all over the country to expand our all-star predictions team. Using the same Google Cloud services that any organization would use to perform data analysis at scale, our team of student developers will be delivering data-driven predictions and insights throughout the tournament. You can see it all in action at g.co/marchmadness—as well as find links to all our training, certifications, resources, and more.
Although our campaign is about college basketball, the NCAA’s challenge in gaining insights from data reflects the same kind of data challenges faced by most enterprises—and many are struggling to find the right skilled workforce to help. We hope this campaign shows how easy and accessible Google Cloud can be for developers everywhere. And we hope that by providing a fun and engaging way to learn our data platform, we can train millions of new Google Cloud developers and help organizations all over the world.
To learn more about analytics on Google Cloud, visit our website.
We are no longer in control of our home directories. My own home directory contains 25 ordinary files and 144 hidden files. The dotfiles contain data that doesn't belong to me: it belongs to the programmers whos...
Let the queries begin: How we built our analytics pipeline for NCA...
March-Madness-ML Applying machine learning to March Madness. Check out my first repo here and my associated
README.md March-Madness-ML Applying machine learning to March Madness. Check out my first repo
openresty - Turning Nginx into a Full-Fledged Scriptable Web Platform
Post with 2446 views. Why is YouTube turning out like this?
Warning: No, this is not the R setup to use if you are a beginner. The RStudio IDE is amazing and should probably always be your default tool. However, if you happen to belong to the outcast realms…
Chrome-only sites are a problem