Data-Driven Analysis for Understanding Team Sports Behaviors

Understanding the principles of real-world biological multi-agent behaviors is a current challenge in various scientific and engineering fields. The rules regarding such as team sports are often largely unknown due to their inherently higher-order interactions, cognition, body dynamics. Estimation from data, i.e., data-driven approaches machine learning, provides an effective way for analysis behaviors. Although most models have non-linear structures high prediction performances, it sometimes hard interpret them. This survey focuses on quantitative understanding invasion basketball football, introduces two main behaviors: (1) extracting easily interpretable features or data (2) generating controlling visually-understandable ways. first approach involves visualization learned representations extraction mathematical behind second can be used test hypotheses by simulating future counterfactual Lastly, potential practical applications extracted rules, features, generated discussed. These contribute better real world.