Over the recent years, Shapley value (SV), a solution concept from cooperative game theory, has found numerous applications in data analytics (DA). This paper provides the first comprehensive study of SV used throughout the DA workflow, clarifying the key variables in defining DA-applicable SV and the essential functionalities that SV can provide for data scientists. We condense four primary challenges of using SV in DA, namely computation efficiency, approximation error, privacy preservation, and interpretability, then disentangle the resolution techniques from existing arts in this field, analyze and discuss the techniques w.r.t. each challenge and potential conflicts between challenges. We also implement SVBench, a modular and extensible open-sourced framework for developing SV applications in different DA tasks, and conduct extensive evaluations to validate our analyses and discussions. Based on the qualitative and quantitative results, we identify the limitations of current efforts for applying SV to DA and highlight the directions of future research and engineering.

翻译：近年来，源于合作博弈论的解概念——沙普利值（SV）在数据分析（DA）领域获得了广泛应用。本文首次对贯穿整个DA工作流的SV使用进行了全面研究，明确了定义适用于DA的SV的关键变量，以及SV能为数据科学家提供的基本功能。我们凝练了在DA中使用SV的四大主要挑战：计算效率、近似误差、隐私保护与可解释性，进而从该领域现有成果中梳理出解决技术，针对每个挑战分析讨论了相关技术以及挑战之间潜在的冲突。我们还实现了SVBench——一个模块化、可扩展的开源框架，用于在不同DA任务中开发SV应用，并进行了广泛的评估以验证我们的分析与讨论。基于定性与定量结果，我们指出了当前将SV应用于DA的研究存在的局限性，并展望了未来研究与工程实践的方向。