Action Valuation in Sports: A Survey

2025-04-08

AI Summary

Current sports analytics lacks a systematic review of action valuation (AV), suffering from weak cross-sport comparability and fragmented methodologies. To address this, we propose the first comprehensive, nine-dimensional AV taxonomy—spanning data, methods, evaluation, and beyond—integrating bibliometric analysis, interdisciplinary method comparison, task-driven modeling, and empirical mapping. Our analysis clarifies AV’s core characteristics, identifies three critical bottlenecks—sparse annotation, causal attribution, and real-time deployment—and distills key metrics for methodological effectiveness. We further articulate four research directions: enhanced interpretability, multi-source heterogeneous fusion, cross-sport transfer learning, and lightweight deployment. This work fills a foundational gap in AV scholarship, establishing a unified theoretical framework and actionable methodology for both generalizable modeling and sport-specific analysis.

Technology Category

• Machine Learning: Evaluation and Analysis
• Knowledge Representation and Reasoning: Action, Change, and Causality
• Computer Vision: Video Understanding & Activity Analysis

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Action Valuation (AV) has emerged as a key topic in Sports Analytics, offering valuable insights by assigning scores to individual actions based on their contribution to desired outcomes. Despite a few surveys addressing related concepts such as Player Valuation, there is no comprehensive review dedicated to an in-depth analysis of AV across different sports. In this survey, we introduce a taxonomy with nine dimensions related to the AV task, encompassing data, methodological approaches, evaluation techniques, and practical applications. Through this analysis, we aim to identify the essential characteristics of effective AV methods, highlight existing gaps in research, and propose future directions for advancing the field.

Problem

• No comprehensive review of Action Valuation in sports exists
• Introduces taxonomy for data, methods, and applications in AV
• Identifies gaps and future directions for Action Valuation

Innovation

• Taxonomy with nine AV dimensions
• Data and methodological approaches analysis
• Evaluation techniques and practical applications