In this engaging discussion, former professional volleyball player Abby Bertics, sports data analyst James Tozer, and Google DeepMind's Petar Veličković delve into the transformative impact of AI on sports. They explore how AI is revolutionizing strategies in basketball and soccer, enhancing player recruitment and game tactics. The guests share insights on predicting injuries, analyzing player interactions using graph neural networks, and the challenges AI faces in capturing the complexities of human performance on the field.
AI has revolutionized sports analytics by enabling teams to refine strategies and recruitment processes through vast data analysis and predictive modeling.
Despite challenges like data quality and the subjective nature of player performance, AI's potential continues to evolve, promising enhanced decision-making in sports.
Deep dives
The Impact of Data Analysis on Basketball Tactics
Data analysis has significantly transformed basketball strategies, particularly with the shift in focus from two-point to three-point shots. A review of game patterns through AI revealed that players had a higher success rate and scoring potential when opting for three-point attempts, which require less precision compared to two-point shots. For instance, players could achieve the same score with a third of their three-point shots as opposed to half of their two-point shots, allowing for greater margin for error. This insight prompted teams to revise their tactics, leading to a style known as 'Morrie ball,' which prioritizes shots from beyond the arc.
The Evolution of Sports Analytics
Sports analytics has evolved from simple statistical tracking to complex AI models that assist teams in recruitment and tactical planning. Initially focused on player selection, analytics began with sports like baseball where discrete, quantifiable data was abundant, leading to successful strategies like those depicted in Moneyball. As the practice expanded, basketball and other sports adopted similar methodologies, utilizing data to inform decisions about which players to recruit or how to devise effective game strategies. The increasing sophistication of analytics has also permeated sports outside of the U.S., demonstrating its far-reaching implications.
Integrating AI in Player Performance Analysis
The integration of AI in sports analytics has advanced the ability to predict player performance and improve training methods. AI models process vast amounts of tracking data and utilize machine learning to make recommendations tailored to players' strengths and weaknesses. For example, by analyzing even the minutest movements of a player's body and the dynamics of their performance, teams can uncover insights into injury risks or areas for skill enhancement. This predictive capability not only aids in player development but also optimizes overall team performance.
The Future and Challenges of AI in Sports
While AI is poised to redefine sports strategies, its successful implementation faces challenges like data availability and the complexity of translating insights into actionable strategies for coaches. The effectiveness of AI models largely depends on the quality and granularity of the data they utilize, which can vary significantly across different sports. Additionally, the subjective elements of player performance, including psychological factors and team dynamics, remain difficult to quantify. Despite these hurdles, the ongoing evolution of AI promises to enhance sports analytics, ultimately leading to more informed decision-making and improved athletic outcomes.
Data has transformed sport in recent decades—from identifying the best place to shoot from in basketball and football, to helping recruit the perfect baseball player. The new age of AI, which can utilise vast amounts of data on players, promises even deeper insights. Teams are experimenting with AI tools that can help pick the best players and prepare the best tactics for individual matches. Perhaps one day these models may even be able to predict injuries. AI models could transform sport—and the experiments with games could also inform the future of AI itself.
Host: Alok Jha, The Economist’s science and technology editor. Contributors: The Economist’sAbby Bertics; James Tozer of Prospect Sporting Insights; Patrick Lucey of Stats Perform; Petar Veličković of Google DeepMind.