As the football league with the highest stadium attendance globally, and broadcast in more than 200 countries, Germany’s Bundesliga is among the leaders of the world’s most popular sport. To increase fan engagement, Bundesliga is leveraging live data streams and historical data from over 10,000 games to build and train ML models in Amazon SageMaker for real-time predictions and additional insights. These models will be deployed as insights and graphics to show fans when a goal is likely to be scored, identify potential goal-scoring opportunities, and highlight how teams are positioning and controlling the field. The league is also working with AWS to deliver fans customized content and search results based on their location, favorite players, teams, and matches, and using Amazon Rekognition to analyze the largest digital football media archive in the world with more than 150,000 hours of video to easily search for historical footage.

FORMULA 1 is the highest class of automobile racing sanctioned by the FIA, with the fastest and most advanced cars. During each race, 120 sensors on each car generate 3 GB of data with more than 1,500 data points being created each second. F1 uses Amazon SageMaker to train deep-learning models with 65 years of data to provide fans with statistics, predictions, and insights into the split-second decisions made by teams and drivers streamed real-time through Amazon Kinesis. Additionally, F1 is using Computational Fluid Dynamics (CFD) run on Amazon HPC for rapid prototyping new body designs in a virtual environment for use in the 2021 season.

NASCAR, the largest stock car racing organization in the US, migrated its 18-petabyte video archive containing 70 years of historical footage to AWS, and can use Amazon Rekognition to auto-tag video frames with metadata, such as driver, car, race, lap, time, and sponsors, and Amazon Transcribe to caption and time stamp every word within speech. This saves NASCAR thousands of hours of manual tagging and searching their video archives to present fans with the most iconic moments in NASCAR history. NASCAR will then use SageMaker to train deep learning models to enhance metadata and video analytics. 

Through its Next Gen Stats (NGS) program built on AWS using machine learning technology, the NFL offers advanced stats that highlight the scale, speed, and complexity of the game. Ultra-wideband receivers track the players and ball movement down to the inch using RFID tags, capturing and storing over 3TB of data each game leveraging Amazon EC2, S3, and EMR. Real-time data is combined with traditional box score data to calculate hundreds of metrics and output predictions and insights delivered through graphics to fans online, onscreen, in stadium, and in second screen experiences, and as APIs to teams, analytics companies, broadcasters, and commentators. 

Founded in 2006 in the UK as Pro Football Focus and now majority owned by former NFL pro Cris Collinsworth, PFF’s team of over 500 analyzes pro and college football using sophisticated mathematics and analytics models. PFF began implementing machine learning solutions with Amazon S3 and AWS ElastiCache to manage scale, having migrated its entire technology and cloud stack to AWS in July 2019. PFF will use AWS compute, storage, database, serverless, analytics and machine learning services to improve operational efficiency, innovate at a faster pace and drive deeper meaning from game statistical data. AWS will enable PFF to uncover never-before-seen metrics that will change the way that teams, fans, and the media experience football.

Considered one of the most tech progressive and data-driven teams in the NFL, the Seattle Seahawks are moving the vast majority of their infrastructure to AWS, leveraging compute, storage, database, analytics, and ML services to drive deep analysis of their players and competitors’ data, improve operational efficiencies, and speed innovation. A data lake on Amazon S3 will combine the team’s 40-plus years of stats with NFL data, player tracking, GPS movement, player health and wellness data, and scouting information for deeper visibility and greater insights enabling coaches to make better matchups and real-time adjustments that will lead to more successful drives and touchdowns.

University of Illinois, Urbana Champaign (UIUC) collaborated with the Amazon Machine Learning (ML) Solutions Lab to help UIUC football coaches prepare for games more efficiently and improve their odds of winning. The team combined UIUC’s deep expertise in college football and coaching with AWS’s machine learning to create a state-of-the-art ML model that predicts the result of any football play. In addition, UIUC coaches now have auto-generated visual game planning sheets based on key features recommended by the ML model. This saves the coaches’ time when preparing for a game, and gives them more insights on their performance and strategies.

Second Spectrum is the Official Optical Tracking and Analytics Provider of sports leagues such as the National Basketball Association (NBA) and the English Premier League. Second Spectrum uses AWS to help sports leagues and their media partners deliver analytics, visualizations, and easily searchable video clips to enhance the fan experience and provide teams with deeper competitive insights. Second Spectrum uses AWS Elemental to minimize latency in its streaming services while offering fans a high-quality viewing experience, and AWS Elemental MediaStore, a storage service optimized for media, to allow television producers and sports commentators to quickly access key moments from sports events.

Swimming is Australia’s most successful Olympic sport and one of the most popular activities in the country with more than 4.5 million people participating annually. Participation in swimming is a fundamental component of Australia’s iconic culture however it relies on government funding and global competition is fierce. Working with AWS, the team has used machine learning models to optimize relay formations, to give the best chance of winning medals at key competitions. AWS is proud to play a role in engaging, supporting and developing the next generation of recreational and elite Australian swimmers. Through this partnership, AWS hopes to support Swimming Australia to increase the sport’s profile and level of media coverage, grow national participation rates and contribute to improved performance outcomes of the Australian national swim team.

For Sportradar, the global provider of sports and intelligence for the betting and media industries providing data coverage from more than 200,000 events annually, advances in computer vision are an opportunity to expand the depth of sports data offered to customers and reduce the costs of data collection through automation. Sportradar is investing in computer vision research both through internal development and external partnerships to build computer vision data collection capabilities with an initial focus on tennis, soccer and snooker. Working with the Amazon ML Solutions Lab, Sportradar is exploring the application of state-of-the-art deep learning models for automated match event detection in soccer, moving beyond player and ball localisation to understanding the intent of the play in terms of what is happening in the game. To bring this technology into production as it matures, Sportradar is leveraging AWS services including Amazon SageMaker, EKS, MSK, FSx and Amazon’s broad range of GPU and CPU compute instances for its computer vision processing pipeline. This infrastructure allows Sportradar's researchers to test and validate computer vision models at scale and bring models from the lab to production with minimal effort while delivering the low latency, reliability and scalability needed for live sports betting use cases.

Using AWS, INEOS TEAM UK can process thousands of design simulations for its America’s Cup boat in one week versus in more than a month using an on-premises environment. The team is using an HPC environment running on Amazon EC2 Spot Instances to help design its boat for the competition. For the hull, whose design needed hundreds of compute cores for every simulation, the team used Amazon EC2 C5 instances in addition to the latest Amazon EC2 C5n Nitro-powered instances with Elastic Fabric Adapter (EFA) network interfaces. To ensure fast disk performance for the thousands of simulations completed each week, the team also used Amazon FSx for Lustre to provide a fast, scalable, and secure high-performance file system based on Amazon Simple Storage Service (Amazon S3).

Pulselive is digital partner to some of the biggest sports leagues and events, from the Premier League to the Cricket World Cup. The Sony subsidiary is helping create fan experiences that increase engagement through new and impactful ways. Pulselive uses Amazon Personalize to enable its customers to create highly personalized recommendations for their online sports media content. Working with the Amazon Prototyping team, Pulselive created a new recommendation engine, increasing video consumption by 20%. By leveraging AWS, Pulselive was able to quickly conduct A/B tests, create a simple proof of concept with minimal disruption, and experiment, keeping the barrier to entry low - both technically and financially.

By tapping into the breadth and depth of AWS services, the NHL will be able to automate video processing and content delivery in the cloud and leverage its Puck and Player Tracking (PPT) System, which runs on AWS cloud infrastructure, to better capture the details of game play for its fans, teams, and media partners. The NHL will work with the Amazon Machine Learning Solutions Lab to apply AWS’s deep portfolio of machine learning services to game video and official NHL data to develop and share advanced game analytics and metrics that take fans deeper into the game. The NHL intends to use AWS Elemental Media Services to develop and manage a cloud-based HD and 4K video content delivery system that will provide a complete view of the game to NHL officials, coaches, players, and fans. Powered by AWS, the system will encode, process, store, and transmit game footage from a series of new camera angles to provide continuous video feeds that capture plays and events outside the field of view of traditional broadcast cameras. By leveraging AWS analytics services including Amazon Kinesis and machine learning services such as Amazon SageMaker, the NHL will be able to audit its feeds to broadcast partners in real time.

AWS is the Official Cloud Provider, Artificial Intelligence Cloud Provider, Deep Learning Cloud Provider, and Machine Learning Cloud Provider of the PGA TOUR. Together, AWS and the TOUR are partnering to transform the way golf content is created, distributed, and experienced, bringing fans closer to the action on the course while also helping the TOUR streamline its media operations. The TOUR will use AWS machine learning, storage, compute, analytics, database, and media services to quickly process and distribute video footage from each golf tournament and will leverage AWS to rapidly transform this content into exciting new digital experiences that provide fans with a more complete and personalized experience across TOUR competition. The TOUR will migrate nearly 100 years of media content to AWS – including video, audio, and images dating back to the 1928 Los Angeles Open – and will stream live footage from future tournaments into the data lake built on Amazon S3. The TOUR will then use Amazon Rekognition to automatically tag content with specific metadata like player names and sponsor logos. The TOUR will also use AWS media services to make it faster to deliver video content for televised event coverage and over-the-top (OTT) streaming for online viewers.

Intel’s Olympic Technology Group set out to develop a machine learning solution to create a real-time digital model of athlete performance to enable a portable, cloud-based elite athlete coaching solution. Intel partnered with the Amazon Machine Learning Solutions Lab (MLSL) to leverage MLSL’s computer vision expertise to enhance Intel’s existing 3D skeletal tracking capabilities. MLSL developed a 3D multi-person pose estimation pipeline on Amazon SageMaker that enables 3D skeletal tracking from a single camera. “The MLSL team did an amazing job listening to our requirements and proposing a solution that would meet our customers’ needs,” said Jonathan Lee, Director of Sports Performance, Olympic Technology Group. The team surpassed our expectations, developing a 3D pose estimation pipeline using 2D videos captured with mobile phones in just two weeks. By standardizing our ML workload on Amazon SageMaker, we achieved a remarkable 97% average accuracy on our models.” 

The Pac-12 Conference is dedicated to developing the next generation of leaders by championing excellence in academics, athletics and the care provided to its student-athletes. Pac-12 Networks, the media company owned by the Conference and its twelve member universities, moved its video and media infrastructure to AWS using AWS Media Services, AWS Cloud Storage and AWS Direct Connect for everything from encoding to ad insertion, transmission to delivery. Pac-12 engineers spin up new services rapidly and cost-effectively using AWS Lambda and Amazon EC2, enabling functionality ranging from cloud-based production to data analytics, in support of the ultimate objective of creating amazing experiences for fans of Pac-12 and college athletics everywhere.

Kayo Sports is a multi-sports streaming service and content aggregator for Australian sports fans, which is running the majority of its IT infrastructure on AWS to deliver personalized customer experiences at scale for more than a million subscribers (as of May 2021). Kayo uses AWS products and services, including analytics, machine learning, media services, and network and content delivery to analyze hundreds of thousands of data points to provide interactive statistics and deeper insights to enhance the viewing experience. This includes SplitView, which enables users to watch up to four sports on one screen, and Kayo Key Moments, which allows users to skip to the best parts of their favorite games. Using services, including Amazon Redshift, Amazon Glue, and Amazon Athena, Kayo analyzes information to create a unified view of the customer, and adjust the content library to deliver a personalized menu of sporting events based on a viewer’s preferences. 

Stats Perform is the market leader in sports technology providing the most trusted sports data and the latest advancements in applying AI and machine learning to deliver better predictions for teams, sportsbooks and a more engaging broadcast, media and fan experience. The company collects the most detailed sports data to create new experiences across sports. Leveraging the richest sports database, Stats Perform enhances sports competition and entertainment through machine learning and computer vision to create advanced predictions and analysis – be that for digital and broadcast media with differentiated storytelling, tech companies with reliable and fast data to power their innovations, sportsbooks with in-play betting and integrity services, or teams with first-of-its-kind AI analysis software. With Amazon and AWS, that’s meant the first-ever use of live win probability in broadcast for Prime’s Premier League coverage, Alexa’s thorough implementation of sports data into voice technology for leagues around the world, advancing the use of rugby data with AWS for the Six Nations Championship, and more. For more information, visit StatsPerform.com. 

Ferrari will use AWS’s proven global infrastructure, including the AWS Europe (Milan) region, and breadth and depth of services to streamline design and testing of its cars, giving customers the most exciting driving experiences possible. In addition, as its new partner, Scuderia Ferrari will leverage AWS to launch a digital fan engagement platform, via its mobile app, to engage hundreds of millions of worldwide fans with exclusive, personalized content. Ferrari will leverage Amazon Elastic Compute Cloud (Amazon EC2), with access to specialized instance types for efficient high performance computing (HPC) and Ferrari will use AWS Graviton2-based instances—which consistently deliver seven times better performance compared to previous generation x86-based instances. Ferrari will build a data lake with Amazon Simple Storage Service (Amazon S3) and use AWS Lake Formation to quickly and securely gather, catalog, and clean hundreds of petabytes of data and will also leverage AWS to make it easier for current and prospective customers to build, purchase, and maintain their cars. Using Amazon Elastic Kubernetes Service (Amazon EKS) and Amazon DynamoDB (AWS’s fully managed key-value database), Ferrari will be able to quickly create, deploy, and scale improved digital experiences such as the Ferrari Car Configurator.