To showcase the power of Google Cloud and its ability to quickly turn data into insights, we used AI and machine learning to make real time, in-game predictions during the March Madness tournament.

Our team of data scientists analyzed decades of NCAA data plus the first half of the game to make a prediction about what would happen in the second half. That prediction would become the basis for a hyper-contextual, real-time commercial.

To pull it off, we created a tool kit of dynamic creative assets that could make a spot about whatever Google Cloud predicted. The tool kit was loaded into custom-built, Google Cloud-powered software that could assemble, edit, render, and traffic a television spot directly to the network in less than 10 minutes (a world’s first).

It was an end-to-end live product demo, in front of 43 million viewers. And Google Cloud nailed the predictions.

Data was core to our executions. Without it, there was no story.

We spent months architecting the data pipeline and creating a set of possible narratives based on the 2018 tournament and matchups. From there, we developed systems that could choose the best narrative given a game’s trajectory and build it into the creative.

Data journey

Leveraging decades of college basketball data, we created models to analyze the data. Those models fed our proprietary software, built using Google Cloud technology. This technology was combined with a team of data engineers who monitored live feeds of the games.

Implementation

We built a workflow for predictive themes like free throws, turnovers, and bench strength. For each theme, we used regression and classification modeling techniques. We trained these models on each team individually, as well as their combined totals, creating 21 prediction options per game.

Data integration

The live data was integrated into the final spots using dynamic creative elements that could be tailored to the prediction.

Application

Using this system, we made six live predictions that aired during the Final Four and Championship games.

1.) Data enhanced consumer experience

We built a live product demo of Google Cloud technology, generating six (6) accurate predictions and six (6) unique real-time ads. All six delivered a data-enhanced, relevant experience for the audience.

2.) Data driven behavior change

7x engagement on Twitter when our prediction ads aired (vs. when paid media went live prior the prediction spots) source: Google Internal Search Metrics, April 17, 2018

3.) Business impact

The campaign drove a 91% lift in product interest and $930K in immediate pipeline impact, a 42% increase in brand search volume, and 30% more new site visits-with a 19% increase in time spent. Source: Google Analytics, 4/17/18, Google Internal Metrics, 4/18/2018

Using decades of NCAA historical data and Google Cloud technology, powered by Artificial Intelligence and machine learning, we made live in-game predictions, during the 2018 NCAA March Madness tournament. In total, six (6) real-time ads with six (6) accurate predictions were made. All six delivered a data-enhanced, contextually relevant experience for the audience.

The goal was to demonstrate Google Cloud’s ability to turn data into insights. As the “Official Cloud of the NCAA,” we decided the March Madness basketball tournament would be the ideal moment to showcase this power. We moved 80+ years of historical NCAA data over to Google Cloud—and with a team of data analysts built models that would allow us to analyze and predict game outcomes, such as the number of rebounds or total three-pointers.

To integrate the real-time data into the commercials, we created a tool kit of dynamic creative assets that could make a spot out of whatever Google Cloud predicted. The prediction was loaded into custom-built, Google Cloud-powered software that could assemble, edit, render, and traffic a television spot directly to the network in less than 10 minutes.

In all, we made six real-time, data-powered spots. All six predictions were wildly accurate. And 43 million viewers enjoyed March Madness insights they couldn’t get anywhere else.

Situation

Ninety percent of the world's digital data has been generated in just the past two years. But only one percent of that data has been analyzed—while the global supply of data will continue to more than double every two years.

C-level executives, IT decision makers, and developers are challenged to make smarter, data-based decisions every day—and AI/ML tools, deployed through cloud-based technology, is the way of the future.

We needed to stand out from traditional B2B advertising and demonstrate the strength of Google Cloud technology to shift perceptions and gain consideration. Source: McKinsey Quarterly, Straight Talk About Big Data, October 2016

Brief

Unlock data to open up amazing new possibilities for everyone.

Objectives

1) Demonstrate Google Cloud via a live product demonstration.

2) Resonate with our core audience as humans, not just business people.

3) Educate businesses on what’s possible when your data’s in the cloud.