Sports tech firm Stats looks to bring A.I. to the broadcast booth and sideline

April 20, 2018 by Ally Marotti, Chicago Tribune

When a baseball announcer rattles off your favorite player's batting average with two outs and runners on first and third, he's not pulling that figure from the back of his mind. There's a good chance that timely information was provided by Stats, a Chicago-based sports data and technology company.

Stats, which gathers data from sporting events around the world for more than 650 customers, says it has inked five deals this year worth a total of more than $70 million. The most recent deal, a $10 million agreement announced last week, extended and expanded a relationship with a global broadcast and telecommunications conglomerate.

Stats plans to invest some of the money into advancing its use of artificial intelligence to capture data, said Chief Revenue Officer Richard Henderson, who declined to name the other parties involved in the deals.

The company, which has already started building out its artificial intelligence team, is working to train computers to review game footage and extract statistics, providing new insights for coaches and players and fun facts for broadcasters to relay to fans.

"There's lots of video footage that exists globally of historic games," Henderson said. "If we can get computers basically to watch the game and code the game, that enables us to aggregate data sources on a much grander scale than individual humans can."

Stats already uses advanced technology to gather data, he said. It deploys employees to stadiums around the world to code games in real time. Its technology can, for example, capture 2,700 data points in a soccer game. It can track the distance a player ran, the trajectory and speed of the ball, how many touches a player had, or how quickly she accelerated.

Artificial intelligence can gather and process even broader data, Henderson said. It can provide predictive analytics to coaches, showing them, for instance, a play in which their players failed to score and recommending a different run that could result in a goal.

"Because we've aggregated so much data, it will know how that defense operates in certain scenarios," Henderson said.

The coaches might not take the suggestion, but the idea is to give them increased insights to help them win.

Such predictive data goes deeper than just capturing statistics broadcasters can share with fans, though that is part of Stats' business. The company counts media and broadcasting companies, as well as sports teams and leagues, among its customers.

For example, Stats will provide data feeds to companies to engage fans during the upcoming World Cup, and coaches in FIFA use the data to strategize. It also distributes football statistics to fantasy sports providers for their platforms and works with Major League Baseball, the National Football League, the National Basketball Association and the National Hockey League.

Teaching computers to watch games and gather data could expand the company's reach to amateur or even high school teams, Henderson said.

The technology wouldn't replace employees; it would do work they don't have time for. The company plans to keep hiring more workers, in the artificial intelligence department and elsewhere. It employs about 1,200 people globally, more than 200 of whom are in Chicago. Earlier this year, it added a floor to its Loop headquarters that can hold an additional 100 employees.

The expanded use of artificial intelligence would allow the company to analyze additional data for more clients as well as historical data. Stats has baseball data going back to the 1800s, for example.

Sheldon Jacobson, a professor of computer science at the University of Illinois at Urbana-Champaign, said the technology Stats is working on would find new value in sports data that are already out there.

"It's the that realizes the potential of the data," he said. "What Stats is really monetizing is the information the data contains."

The will help coaches make better decisions and ultimately improve performance, Jacobson said. But once other teams catch on, the value of the information could wane. He pointed to the way Michael Lewis' book "Moneyball" brought widespread attention to the Oakland Athletics' use of advanced statistics. Once other baseball teams caught on, the A's lost some of their edge.

Stats will need to keep innovating, he said.

Explore further: Twitch will stream NBA G League games and let its livestreamers do play-by-play

Related Stories

The NFL joins the data revolution in sports

September 22, 2016

In some potentially game-changing news for the way we understand professional football, the National Football League began the 2016 preseason by placing tracking sensors in its footballs for the first time. The chips are ...

Fantasy sports company DraftKings raises $300 mn

July 27, 2015

DraftKings, a leading player in the booming fantasy sports business, announced Monday that it raised $300 million from a group of investors that includes Fox Sports and three major sports leagues.

NBA to install motion cameras in every arena

September 9, 2013

The NBA announced Thursday that it will install motion-tracking cameras in every arena this season to provide coaches, players and fans reams of data aimed at pulling back the curtain on what it takes to succeed at basketball's ...

Recommended for you

In colliding galaxies, a pipsqueak shines bright

February 20, 2019

In the nearby Whirlpool galaxy and its companion galaxy, M51b, two supermassive black holes heat up and devour surrounding material. These two monsters should be the most luminous X-ray sources in sight, but a new study using ...

When does one of the central ideas in economics work?

February 20, 2019

The concept of equilibrium is one of the most central ideas in economics. It is one of the core assumptions in the vast majority of economic models, including models used by policymakers on issues ranging from monetary policy ...

Research reveals why the zebra got its stripes

February 20, 2019

Why do zebras have stripes? A study published in PLOS ONE today takes us another step closer to answering this puzzling question and to understanding how stripes actually work.

Correlated nucleons may solve 35-year-old mystery

February 20, 2019

A careful re-analysis of data taken at the Department of Energy's Thomas Jefferson National Accelerator Facility has revealed a possible link between correlated protons and neutrons in the nucleus and a 35-year-old mystery. ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.