Explaining the "Why": A Unified Framework for the Additive Attribution of Changes in Arbitrary Measures

2026-04-28

AI Summary

Existing attribution methods struggle to simultaneously achieve generality, holism, and interpretability, limiting their ability to effectively explain the root causes behind changes in aggregate metrics. This work proposes the first unified attribution framework applicable to arbitrary metrics, grounded in cooperative game theory. By categorizing metrics according to their mathematical structure, the framework combines closed-form solutions with approximation algorithms to strike a principled balance between generality and computational efficiency. It supports flexible attribution ranging from approximate to exact and accommodates both additive and non-additive metrics. Empirical evaluations demonstrate its numerical accuracy and broad applicability, while case studies highlight its interpretability advantages. In real-world root cause analysis tasks, the method significantly outperforms existing systems.

Abstract

Explaining why aggregated measures change is a critical challenge in data analytics that existing systems struggle to address. While current attribution methods exist, they lack a unified solution that is simultaneously general for arbitrary measures, holistic across both data dimensions and measure composition, and rigorous in its interpretability. To bridge this gap, we introduce a principled framework that reframes attribution through the powerful lens of cooperative game theory. Our key contribution is a classification of measures based on their mathematical structure, which enables a spectrum of algorithms-from general approximations to exact, closed-form solutions-that offer a principled trade-off between generality and performance. We demonstrate our framework's superiority through a multi-faceted evaluation: simulations first confirm its numerical accuracy and then its generality for non-additive measures; a case study on Simpson's Paradox showcases its unique interpretability; and a final experiment proves its practical utility by significantly outperforming existing root cause analysis systems.

Problem

• attribution
• aggregated measures
• interpretability
• data analytics
• measure change

Innovation

• attribution
• cooperative game theory
• measure decomposition
• interpretability
• root cause analysis