How Arccos Golf is using AWS and generative AI to transform the game (SPT211)

Summarizing the Video Transcript

Introduction

  • The speaker is Ryan Johnson, the VP of Software Engineering at Aros Golf.
  • Aros Golf is a golf tracking app that helps golfers improve their game by providing data-driven insights.
  • The presentation focuses on how Aros Golf is using generative AI to make golf more accessible and help people improve their game.

The Challenge with Analytics

  • People generally have an aversion to math and data, which is a common challenge in the field of analytics, both in golf and in business.
  • Basic analytics, such as the number of putts, are easy to comprehend but have low value. More advanced metrics, like Strokes Gained, are highly informative but complex and inaccessible to the average golfer.
  • The speaker mentions that Aros Golf has partnered with a data analyst, Eduardo Moliner, to provide high-quality analytics, but this approach is not scalable.

Aros Golf's Approach

  • Aros Golf has leveraged Amazon Bedrock, a generative AI service, to develop a product that helps golfers understand their game better.
  • The key goals were to quickly prove the concept, personalize the output, avoid repeating statistics, and focus the user's attention on the most relevant insights.

Technical Challenges and Lessons Learned

  • Orchestrating the data flow and integrating the LLM into the report generation process was more time-consuming than expected.
  • Model selection and prompt optimization were crucial for achieving the desired quality of output at the right cost.
  • The data format (XML) and the separation of analysis and summarization were important factors that improved the performance.
  • Ensuring the accuracy of the LLM-generated content was a significant challenge, which was solved by using a separate prompt to evaluate the output and correct any inaccuracies.

Leveraging LLMs for Golf Analytics

  • The golf industry presents unique challenges, such as the vast number of golf courses, tee boxes, and golfers of various skill levels.
  • Determining the location of the golf pin on a given day is a critical piece of information for accurate analytics, and the speaker showcases how Aros Golf used an LLM to extract this data from pin sheets.
  • The speaker emphasizes the potential for leveraging LLMs in various phases of the data capture, analysis, and communication process to drive meaningful impact for golfers.

Conclusion

  • The speaker encourages the audience to explore the potential of LLMs in their own businesses and applications, particularly in the areas of data capture, analysis, and communication.
  • He invites the audience to further discuss golf analytics and the use of LLMs after the presentation.

Your Digital Journey deserves a great story.

Build one with us.

Cookies Icon

These cookies are used to collect information about how you interact with this website and allow us to remember you. We use this information to improve and customize your browsing experience, as well as for analytics.

If you decline, your information won’t be tracked when you visit this website. A single cookie will be used in your browser to remember your preference.

Talk to us