NFL and AWS Expand Partnership to Enhance Fan Experience with AI Technology

The NFL and AWS expand their partnership to tackle more AI use cases - SiliconANGLE

The NFL and AWS expand their partnership to tackle more AI use cases Just in time for the 2024 season, the National Football League and Amazon Web Services Inc. continue to push the boundaries of artificial intelligence and machine learning in football. Through a partnership that began in 2017, the NFL has used AWS technology to improve player performance analysis, game strategies and fan experiences. Upcoming NFL games will showcase a new AI-powered tool, Tackle Probability, that analyzes and predicts the likelihood of a defender making a tackle in real time. The tool identifies the most dependable defenders and the hardest-to-catch ball carriers. It also provides data on key performance metrics, such as missed tackles and successful attempts, offering teams valuable insights for offensive and defensive strategies. More specifically, Tackle Probability looks at 20 different factors, including the position and speed of each defender, every 10th of a second. Using these data points, an AI model, trained on five years of past game data, calculates the likelihood of a tackle happening at any given moment in a play. From this data, the model creates new stats like how often defenders attempt tackles without missing or how frequently running backs force missed tackles. This helps coaches see which players are the most reliable at tackling or avoiding tackles. Tackle Probability is a feature within Next Gen Stats, the NFL's player and ball tracking platform, which relies heavily on AWS to process an enormous amount of data collected from games. The platform gathers over 500 million data points each season, providing the NFL with advanced statistics that improve the viewing experience and aid gameplay decisions. This includes rule changes such as the new Dynamic Kickoff to minimize high-speed collisions and injuries during kickoffs by adjusting player positioning and movement. Digital Athlete is another tool developed using AWS to improve player safety. The tool simulates game and practice scenarios to help coaches and medical staff assess injury risks so they can develop prevention and recovery plans for each player. One could think of this as building a digital twin of players and then running them through various scenarios to better understand when and how injuries occur. Teams can use that data to avoid those situations and keep the players on the field longer. In addition to improving player safety, AWS is working with NFL Media to implement Amazon Q Business, an AI assistant that answers business and production-related questions. It acts like an automated helpdesk for common technical or operational inquiries. NFL Media also introduced an Amazon Bedrock-powered research tool that allows production teams to gather insights and footage from specific plays in the NFL's Next Gen Stats database using simple language prompts. The NFL believes these developments will boost productivity by automating routine tasks and speeding up research. Rather than spending time on repetitive activities, teams can focus on creating high-quality content across NFL Media's properties, such as the NFL Network, NFL Films, NFL.com, NFL+, the NFL app and social media channels. Many innovations, including Tackle Probability, are inspired by submissions from the AWS Big Data Bowl, created five years ago to develop new ways of using the NFL's Next Gen Stats. The program creates an open platform for engineers, data scientists, students, and others without sports experience to get involved in football analytics. The competition has grown fourfold since its inception in 2019, with more than 230 submissions from 400 participants last year and participants from more than 75 countries in the half-decade that it has run. By democratizing access to data, the NFL and AWS can accelerate creativity and innovation. For the participants since the inception of the Big Data Bowl, more than 50 participants have landed jobs in professional sports analytics, with 30+ being hired by NFL teams or player-tracking vendors. Sports leagues have a wealth of data, much of which has gone untapped for decades. One of the challenges is finding experts who understand data and the respective sport to derive value. Generative AI enables anyone, with or without a data sciences or sports background, to find new ways of leveraging that data to deliver operational value and create new fan experiences.

Amazon says its football AI can predict blitzes

The new Thursday Night Football system will tackle 'a huge hole in our football stats toolbox.' Amazon is investing substantial artificial intelligence computing power into its NFL Thursday Night Football broadcasts. According to a September 10 announcement, Tackle Probability is a new machine learning model that analyzes, interprets, and possibly predicts impending defensive blitzes against quarterbacks. Debuting during the Prime Video livestream of the Miami Dolphins vs. Buffalo Bills game on September 12, Tackle Probability's results can be used by both real-time commentators, as well as provide "new ways of visualizing the action on the field." As GeekWire explained on Tuesday, this will include on-screen highlighting of the defensive players most likely to attempt tackles. "Until now, tackling statistics were limited to simple counts of solo and assisted tackles," Amazon Web Services (AWS) said in a statement. "[The] new tackle probability model aims to capture the entire process of tackling, from pursuit angles to missed attempts, providing a wealth of deeper and more granular insights..." Tackle Probability is the latest outcome from the NFL Big Data Bowl, an annual crowd-sourced competition intended to "make the game more exciting to fans" by developing new tools using analytics and tech. Amazon designed the system in less than six months by first training the AI on millions of data points from every NFL game between 2018 and 2022, then using last season's games as a test set. While "traditional stats only tell part of the story" according to an AWS explainer video, Tackle Probability relies on massive amounts of player and team statistics to reach its near instantaneous predictions. "We fully tested 15 different machine learning models on over a million data points in four months, and now we can run the model in a live setting where it's going through hundreds of thousands of data points every second, millions per game," Keegan Abdoo, Research Analytics Manager, NFL Next Gen Stats, said in a statement. For example, AI can analyze within milliseconds all 11 on-field defensive players using 20 specifically identified factors like their career tackle yards saved, chase down attempts, and missed tackle yards lost. This produces over 20,000 data points for Tackle Probability to interpret near-instantaneously ahead of a 10-second-play. Its conclusions can then be shown via onscreen animations, interpreted by live broadcast commentators, and later utilized by teams during postgame reviews. "Football is games within games, and it's been tough to find stats that truly quantify tackling beyond just the outcome," added Mike Band, Senior Manager of Research and Analytics, NFL Next Gen Stats. "It was a huge hole in our football stats toolbox and an area where we knew we needed more quantified metrics." Amazon vows that Tackle Probability's "unprecedented insights" will result in "game-changing" strategies on the field. Usage examples from the company include NFL team coaches employing the stats to determine which players are the most consistent and accurate at tackling -- something they are already doing. Broadcasters, meanwhile, can highlight broken or made tackles for audiences "in real time." Which, again, is part of what makes live NFL game broadcasts "live." Still, Tackle Probability is just one component within a fleet of similar NFL partnerships dedicated to stats, calculating season schedules from "a quadrillion possible combinations," generating new NFL Films and NFL Media content, and analyzing fan behavior. Another area of benefit is allegedly improving player safety and mitigating injuries -- the Digital Athlete tool, for example, was "instrumental in informing recent rule changes" after simulating 10,000 seasons of football to identify the biggest physical concerns facing athletes during any given game. [Related: 'The world is not prepared.' How AI energy thirst might tap into geothermal power.] Amazon's newest AI rollout comes during the second year in its 10-season, $100 million partnership deal with the NFL for broadcasting rights to Thursday Night Football through Prime Video. In July, Amazon entered into an agreement with the NBA that will see the Big Tech company dole out $1.8 billion annually to air 66 games each season for the next 11 years. It's a safe bet to assume similar AI analysis will arrive for Amazon's basketball coverage in the near future.

Amazon adding AI prediction technology to NFL games

Amazon is planning on incorporating artificial intelligence (AI) as part of its predictive technology for broadcasts of NFL games this season. Debuting this season will be Amazon Web Services' (AWS) Tackle Probability model, which will predict, at any given moment of a play, the likelihood that a given defender will make a tackle, helping to quantify which defenders are the most reliable tacklers and which ball carriers are most elusive, the company said. Tackle Probability can be used to calculate various metrics that can be applied to both offensive and defensive analysis, such as missed tackle attempts by a defender and missed tackles forced by a ball carrier. Powered by AWS, the company's Next Gen Stats platform says it collects more than 500 million data points each season. "Through our collaboration with AWS, we are continuously pushing the boundaries of what's possible in football," said Gary Brantley, chief information officer at the NFL. "By harnessing the power of data and advanced technologies like generative AI, together we are accelerating the pace of innovation in important areas such as player safety, fan engagement and content production. This season we'll see an increase in operational efficiency as we begin to leverage AWS's generative AI capabilities at NFL Media." Amazon is one of several large tech companies that have invested billions into the NFL specifically and live sports programming more generally in recent years. Other major media brands, such as ESPN, have teased plans to implement AI into leading programs and live broadcasts. Amazon's first "Thursday Night Football" broadcast of the season is this week, when the Miami Dolphins host the Buffalo Bills in prime time.

Amazon's AI feature for NFL broadcasts predicts which defensive players will blitz the quarterback

AI seems to be everywhere these days -- even on the screen during live NFL games. Amazon is kicking off another slate of Thursday Night Football games, part of a decade-long deal it inked with the NFL to exclusively stream live action every week during the NFL season. A new feature coming to Amazon's main TNF feed this year is called "Defensive Alerts." It uses AI and predictive modeling technology that tracks the movement of defensive players before a play and tries to determine who is most likely to rush the quarterback. A red orb appears around the moving players to help viewers spot potential blitzers. "It really gives the fans a bit of insight as to who could be rushing the quarterback and changes the way they view the game," former NFL cornerback Richard Sherman, now an NFL analyst for Amazon, said in a press release. The feature was tested in Amazon's alternate TNF feeds last year and now it will be used in the main broadcast for each game this season, starting with the Miami vs. Buffalo matchup Thursday. Amazon experiments with a bevy of analytics-focused features as part of an alternate broadcast called Prime Vision with Next Gen Stats that fans can access while watching via Amazon.com, Fire TV, or Prime Video app. New features in the alternate feed this year include "Pressure Alert," which highlights defensive players in position to disrupt a play, and "Coverage ID," which uses live player tracking data to show defensive schemes before the ball is snapped. There's also "Defensive Vulnerability," which identifies areas on the field where the offense should attempt to attack. "When I watch a game, I like to see how the pre-snap motions force the defense to adjust," Kirk Herbstreit, a longtime commentator and analyst on TNF, said in a statement. "The new Defensive Vulnerability feature will show exactly where the offense should exploit mismatches." Of course, not every fan may want to watch a game in the same way as commentators or former players. So it makes sense that Amazon appears to take a methodical approach to adding any fancy tech features to the main TNF stream. Amazon this season will broadcast an NFL playoff game for the first time, streaming a Wild Card matchup later this year. It's also streaming a game on Black Friday after doing the same last season. The company integrated e-commerce shopping features as part of the game feed last year, offering a potential glimpse at the future of advertising during live sports. Amazon paid a reported $100 million for the TNF deal. It's part of Amazon's growing sports streaming catalog that will also include NBA games starting in 2025. As more people cut the cord, sports leagues are increasingly engaging with tech companies as their existing deals with traditional cable providers expire. Those companies are hungry for valuable content such as live sports -- one of the most-watched telecasts -- to draw more subscribers to their respective platforms. For Amazon, the streaming deals offer a way to boost Prime memberships, which are required to watch games. It also opens up more revenue opportunities via advertising, which has become one of Amazon's most profitable businesses.