Slide 1

Slide 1 text

No content

Slide 2

Slide 2 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. Machine Learning as a teammate: How data is changing sports today

Slide 3

Slide 3 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. The future? MORE DATA

Slide 4

Slide 4 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. How Machine Learning changes the game today Unlocking data’s potential Engaging and delighting fans Increasing the pace of innovation changing how we automate, analyze, and leverage data for leagues and teams enriching the fan experience before, during, and after games using data to innovate around performance, health, and safety

Slide 5

Slide 5 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. The stats tell the story Unlocking data’s potential

Slide 6

Slide 6 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. We capture more data every year… Unlocking data’s potential

Slide 7

Slide 7 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. …and this is only going to grow Unlocking data’s potential

Slide 8

Slide 8 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. NHL uses AI to deliver real- time face-off predictions to analysts, fans, and teams Prediction shown live before the play happens to allow fans to determine which player is most likely to win. Built by analyzing over 200,000 face-offs combined with 10 years of historical player data. Unlocking data’s potential

Slide 9

Slide 9 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. Deployed Model Endpoint Engaging and delighting fans Prepare data Store features Detect bias Build with notebooks Manage & monitor Train models Deploy in production Tune parameters Explain predictions CI/CD AMAZON SAGEMAKER STUDIO IDE

Slide 10

Slide 10 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. 36 Clubs Engaging and delighting fans People want to experience the game differently

Slide 11

Slide 11 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. Content Personalization Bundesliga NEXT App Engaging and delighting fans +17% increase time spent in app +24% more sessions per user +67% more articles read per user

Slide 12

Slide 12 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Personalize Customized personalization API Item metadata (details of articles, products, videos, etc.) User metadata (age, location, etc.) User events/interactions (views, signups, conversions, etc.) Engaging and delighting fans

Slide 13

Slide 13 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. What fans want: wheel to wheel racing Increasing the pace of innovation

Slide 14

Slide 14 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. Running in dirty air behind another car, a 2019 machine could lose more than 40% downforce. But with the 2022 car design, this drops to around 10%, with airflow coming off the new cars both cleaner and directed higher, meaning it has significantly less impact on drivers following, giving them the chance not just to overtake, but to battle. Increasing the pace of innovation

Slide 15

Slide 15 text

No content

Slide 16

Slide 16 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. How F1® designed the 2022 car F1 use AWS ParallelCluster to manage High Performance Compute (HPC) clusters of Amazon EC2 instances across three AWS Regions. Intel, AMD and Graviton-based instance types are leveraged to achieve optimum performance and price configurations, along with Amazon EC2 Spot capacity for additional cost savings. By using AWS for CFD, F1 benefit from: Time gains for single simulations Parallel running of multiple simulations The use of Machine Learning to optimize CFD simulation A W S I S H O W

Slide 17

Slide 17 text

No content

Slide 18

Slide 18 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. Unlocking data’s potential Engaging and delighting fans Increasing the pace of innovation

Slide 19

Slide 19 text

© 2022, Amazon Web Services, Inc. or its affiliates. All rights reserved. Learn more and get started at aws.amazon.com/sports