IBM Watson and ESPN use AI to transform fantasy football data into insight
If you play fantasy football, you are no stranger to the concept of data-driven decision making. Every week during football season, an estimated 60 million Americans pore over player statistics, point projections, and trade proposals, looking for that elusive insight that will guide their roster decisions and lead them to victory.
But numbers only tell half the story. And for the past six years, ESPN has worked closely with IBM to help tell the other half.
Every football season, millions of articles, blog posts, podcasts and videos are produced by the media, offering expert analysis on everything from player performance to injury reports. But for decades, this treasure trove of expertise went largely untapped by fantasy footballers, who could only consume a tiny fraction of this highly valuable content. Not anymore.
To identify and distill the insights locked inside this sea of “unstructured” data, ESPN collaborated with IBM to teach Watson the language of football. And today, using the natural language processing of Watson Discovery, ESPN serves up billions of AI-powered insights to the 11 million people who play fantasy football on the ESPN Fantasy app.
AI-powered insights that enhance the fantasy football experience
Fantasy sports is more than fun and games. It’s also a USD 8.8 billion industry. And for ESPN, fantasy football is a critical driver of digital engagement. To keep its experience fresh and competitive, ESPN needs to introduce new features and enhancements that drive customer satisfaction and new membership.
“We want ESPN to be the destination for all fans playing Fantasy Football, whether it’s their first time or they’ve been managing a league for 20 years,” says Chris Jason, Executive Director, Product Management at ESPN. “To meet that bar, we have to continuously improve the game and find ways to enhance the experience with new innovations.”
To help, ESPN partnered with IBM Consulting using the IBM Garage methodology to better understand the kinds of data-driven insights fantasy players want. Together, they created two unique features that are now integrated into the ESPN fantasy football app: Player Insights with Watson and Trade Analyzer with Watson.
Using deep neural networks and advanced natural language processing, Player Insights with Watson combines the analyses of both structured and unstructured data to help fantasy managers compare players, estimate the potential upside and downside of starting a particular player and even assess the impact of an injury. It lets a fantasy owner visualize the risk-and-reward scenarios, see trends over time and field a more competitive team.
“Because we’re incorporating insight from media experts, it presents a more comprehensive analysis of a player’s potential on any given week,” says Aaron Baughman, Distinguished Engineer, and Master Inventor with IBM Consulting.
Player Insights are built on containerized apps using Red Hat OpenShift running on the IBM Cloud. A machine learning engine pulls dozens of models from cloud object storage (running in Dallas and Washington, D.C., to ensure continuous availability).
Watson ingests and analyzes millions of news stories, opinion pieces by fantasy experts and reports on player injuries. The resulting insights are then correlated with traditional statistical data on more than 1,900 players across all 32 teams to help fantasy managers decide which players to start weekly.
Encouraging trades and transactions
Trade Analyzer with Watson uses those same Player Insights to evaluate potential trades. A visual UI shows a fantasy manager which positions they need to fill to improve their roster. These team needs are prominently displayed at the top to guide the manager’s trade journey. When one manager proposes a transaction, Trade Analyzer automatically assesses the strengths and weaknesses of both rosters.
When managers initiate transactions with each other, Trade Analyzer with Watson delivers trade insights, which feature a grade for each athlete involved in the trade and a grade for the overall value of the trade. As a result, with one look, managers can tell if their trade is a good deal. Once the managers have these insights, they can move ahead with the trade, cancel it or edit the trade package.
“An active league is a fun league,” says Jason. “So we want to encourage roster moves and trading between teams. These features help us do just that.”
Throughout this six-year partnership, Watson has produced hundreds of billions of AI-powered insights for ESPN and its viewers. In just the first week of the 2022 season, users proposed more than 6 million trades via ESPN’s platform. And last year alone, IBM served more than 34 billion AI-powered insights through the ESPN fantasy app.
Trade Analyzer and Player Insights with Watson use AI to foster better decisions by fantasy managers. But they also make ESPN Fantasy Football more fun and engaging. And the partnership with ESPN allows IBM to demonstrate AI’s ability to transform massive quantities of data into meaningful insight, a capability business leaders are looking for in every industry.
The post IBM Watson and ESPN use AI to transform fantasy football data into insight appeared first on Journey to AI Blog.