IBM and ESPN Fantasy Football

IBM Consulting and ESPN work together to infuse the ESPN Fantasy app with popular AI-powered features, like the Boom-and-Bust analyses, Trade Grades, and Waiver Grades. And this year, they added the IBM watsonx Fantasy Insight Weekly, an AI-generated overview of intriguing players, each meeting the criteria of a variety of data-driven categories. Want to find some Diamonds in the Rough? Need a Sure Thing? Or maybe some Trade Bait? The AI of IBM watsonx has you covered.

The AI-generated insights found in the ESPN Fantasy app are produced by transforming a massive volume and variety of football data into meaningful insights. To centralize, integrate, and prepare this data – which comes from multiple sources – ESPN uses watsonx.data, the only hybrid, open data lakehouse for enterprise AI and analytics.

To help foster more trust in the app’s AI-generated insights, ESPN asked IBM if it could help fantasy team owners understand why players were assigned particular grades. To do it, the team trained a generative AI model called IBM Granite to add “Contributing Factors” to each Trade Grade and Waiver Grade, explaining the logic behind the numbers.

To develop the AI features in the ESPN Fantasy app, the team took advantage of a powerful AI assistant to increase the efficiency and accuracy of its code. IBM watsonx Code Assistant™ uses generative AI from a purpose-built Granite model to accelerate software development, helping developers generate code based on natural language prompts. The team used the tool to analyze and explain snippets of code, annotate code to facilitate better collaboration between developers, and auto-complete snippets of analyzed code.

Power up your knowledge of AI with the IBM SkillsBuild program, which offers free courses and resources for learners, educators and organizations. Explore the basics of AI, including foundational concepts about the kinds of AI used in the ESPN Fantasy app.