Big Data and the Big Game: Super Bowl 50
It’s almost time for the big game–the one and only, Super Bowl—and this year promises to be even bigger and better than ever. Super Bowl 50 takes place Feb. 7, 2016, at Levi's Stadium in Santa Clara, California, where 75,000 people are expected to cram in for the game. But even more than that number are expected to be watching from home or elsewhere via broadcast and online.
Last year’s epic game between the Patriots and the Seahawks was the most watched broadcast in U.S. TV history with an average audience of 114.4 million viewers. Even the halftime show by Katy Perry during the 2015 Super Bowl earned the ‘most-watched’ performance in Bowl history. And while most fans may not notice the difference, big data has the potential to change the Super Bowl experience in several ways.
Retailers Looking to Data as Product Demand Scales
As millions of Americans pick up their favorite snacks for Super Bowl parties, sports experts are spending hours on end pontificating on the minutiae of the tiniest details happening both on and off the field in an effort to predict the winner of the big game. So as living rooms pack out with casual and diehard fans alike, it’s estimated that over a BILLION chicken wings, 11.2 million pounds of potato chips, 8.2 million pounds of tortilla chips, 3.8 million pounds of popcorn and three million pounds of nuts will be consumed during Super Bowl 50. With numbers like those, retailers better be sure to stock up on their supplies in time for kick-off—a key area where big data can help.
Using Data to Predict the Outcomes
What remains to be seen is whether or not this year’s matchup between the Denver Broncos and Carolina Panthers or the halftime show performed by Coldplay, Beyonce and Bruno Mars will be able to top 2015 records. This is the third straight season wherein the top seeds from each conference are facing off in the Super Bowl. It’s happened only three times since 1990 prior to this stretch. A victory in Super Bowl 50 would give Peyton Manning his 200th career win, including playoffs. Manning would be the only QB in NFL history with 200+ wins, surpassing Brett Favre (199 wins, including playoffs) for the greatest number of wins overall.
One of the favorite pastimes in all sports, not just the NFL, is to predict the outcome of each contest. Predicting a Super Bowl winner is far from an easy task, especially when both teams are so evenly matched, but many experts have turned to big data in the hopes it can provide added insights on game outcomes.
In the average football game, there are numerous data points that sports analysts track—from individual player performance to overall team stats. This is an area where big data can take insights to the next level—measuring things like total distance each team will travel to get to the game, the impact of weather conditions on individual plays, and comparisons between different player matchups. Another data set used in today’s NFL: equipping each player with sensors in shoulder pads so that coaches can access detailed location data on each player, and from that data, analyze things like player acceleration and speed.
From all these different stats and figures, big data algorithms can be created to come up with an eventual winner in any game. The challenge to create the most accurate algorithm is one that a handful of businesses and institutions have already looked at in the past. For example, one company, Varick Media Management, created their own Prediction Machine that boasted a 69 percent accuracy rating during the 2013-2014 NFL regular season as well as an impressive record for other championship games. Facebook also tries to predict a winner from an analysis of social media data. Speaking of, in 2015 over 28.4 million tweets related to the game and halftime show were sent during the live telecast—making it the most tweeted Super Bowl ever.
Even though these algorithms take into account a lot of data, the results are far from being 100 percent accurate. After all, while Varick Media Management accurately predicted the Seahawks would win last year’s Super Bowl and Facebook predicted a Denver Broncos victory in 2014, which ended up being a blowout loss to the Seahawks.
Going beyond sports analysis and the big game, big data may have a big impact on the thing many fans anticipate most: the commercials. Super Bowl ads cost millions of dollars; and research seems to show that only about 20 percent of those ads lead to more products sold. Additionally, with big data collected through social media listening tools, companies can potentially get a picture of what people talk about most before, during, and after the game. Hence, using big data analysis tools, companies can potentially create more targeted advertising campaigns to drive more engagement, making their Super Bowl ad a better return on investment.
The Super Bowl remains an exciting game that tens of millions of people around the world will enjoy, but many aspects of the game are likely to change as we continue to thrive in the era of big data. Whether it be in terms of predicting the most likely winner of the game or how advertising is handled, big data stands to have a significant impact. In the meantime, fans can still watch some of America’s most skilled athletes perform at their best!