AI tool uses data to redefine sport sponsorships

In pro and college sports, sponsorships mean more than a logo on a jersey or signs at a stadium. The revenue these agreements generate is as pivotal to an organization’s success as ticket sales and media rights. Despite the billions that franchises and programs invest each year, the tools they use to forecast the value of sponsorships lag behind the analytics they use to measure performance on the field.

Dr. Jonathan A. Jensen, associate professor in the Department of Kinesiology and Sport Management at Texas A&M University, is looking to close that gap. Drawing on a decade of research into sponsorship analytics, and with help from computer science students in the College of Engineering, Jensen led the development of the Sport Sponsorship Predictive Artificial Intelligence Network (SSPAIN.ai), a tool designed to provide a more precise picture of sponsorship valuations and a clearer financial future.

Sponsorship deals often rely on instinct, relationships and precedent instead of data. This may leave organizations vulnerable to uncertainty. SSPAIN.ai addresses this issue through an advanced machine learning algorithm trained by data from more than 5,800 sponsorships, spanning 23,000 observations across the globe. Using survival analysis, which is more commonly used in fields like public health, the tool can forecast the probability that a sponsor will renew in the future and the expected duration of the sponsorship agreement.

Through SSPAIN.ai, teams and leagues can be less reactive and more strategic in the way they manage their portfolios. “SSPAIN.ai was built to give sports organizations a clearer picture of their future sponsorship revenue,” said Jensen. “This helps them identify which partners are most likely to renew and which ones need attention, so they can make smarter decisions and maximize value.” As capital from private equity firms and venture capitalists (VCs) continues to flow into sports, the ability to quantify sponsorship value will become more critical in valuing each franchise.

SSPAIN.ai is already generating interest from the college and professional ranks, including Texas A&M Athletics, the Dallas Mavericks, the National Football League, Playfly Sports, 23XI Racing and other sports leagues, teams and agencies.

For students and faculty, this initiative also represents an example of how research can shape the way an industry functions. It has been especially inspiring for the computer science students who helped develop SSPAIN.ai as part of a capstone project, combining expertise in sport management, data science and software engineering. “Their collaboration across modeling, UI/UX, product ownership and security allowed them to iterate quickly on feedback from both the sponsor and external executives,” said Pauline Wade, professor of practice in the Department of Computer Science and Engineering.

Grant Martinez, one of the students on the project, said the hours of research helped him better understand survival analysis despite coming in with little experience in statistics. “This project gave us great exposure to real-world user feedback and when multiple executives from sports franchises around the nation tested our product,” he said.

Jensen sees SSPAIN.ai as a pre-seed investment opportunity for VC firms or as a valuable acquisition by a major league or franchise, positioning the tool as the gold standard in sponsorship predictive analytics. Jensen is planning to showcase it at the MIT Sloan Sports Analytics Conference trade show in Boston in March, as the statistical foundation of SSPAIN.ai was first presented at the Sloan conference as part of the finals of its research papers competition in 2017.

“Our ultimate goal is to give sports organizations confidence in their financial future,” he said. “By turning sponsorship data into actionable insights, we’re helping teams and leagues make smarter decisions that will shape the business of sports for years to come.”