A Unified Approach to Interpretable Causal Root Cause Attribution
Abstract
Understanding why a target metric changes is a fundamental problem in data-driven decision making, beyond anomaly detection alone. We study root cause attribution for metric changes in complex e-commerce systems, focusing on trade-offs between interpretability, efficiency, and causal validity. As a starting point, we extend a metric-decomposition method into a recursive metric-tree framework for multi-level root cause analysis, but this relies on independence and decomposability assumptions that miss complex causal dependencies. In contrast, graphical causal models (GCMs) relax these assumptions and improve causal validity, at the cost of interpretability, higher computational and data demands, and potential attribution target misalignment. Through real-world applications, mathematical proofs, and simulations, we characterize the fundamental sources of these trade-offs. Guided by these insights, we propose a unified, causally informed attribution approach that integrates structural causal information into the metric-tree decomposition framework and corrects key sources of misalignment in GCM-based causal attributions, substantially improving causal validity while preserving interpretability and fast computation. Analytical proofs and simulations demonstrate that the proposed approach produces more accurate root cause attributions, and we also present a real-world application.
Related
- Beyond Conditional Independence: Root Cause Analysis with Deep Causal Models
- Retrospective Causal Attribution under Case-Control Sampling
- Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths
- What Moved the Alarm Score? Causal Attribution with Exact Computation and Scarce-Incident Estimation
- Interpretable Causal Discovery via Causal-Effect Constraints
BibTeX
@misc{zhou2026unified,
title = {{A Unified Approach to Interpretable Causal Root Cause Attribution}},
author = {Jing Zhou and Dominik Janzing and Sepp Tsang and Patrick Blöbaum and Marco Visentini Scarzanella},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.29735},
eprint = {2608.29735},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.29735},
}
RIS
TY - UNPB
TI - A Unified Approach to Interpretable Causal Root Cause Attribution
AU - Jing Zhou
AU - Dominik Janzing
AU - Sepp Tsang
AU - Patrick Blöbaum
AU - Marco Visentini Scarzanella
PY - 2026
DA - 2026/08/30
PB - arXiv
DO - 10.48550/arxiv.2608.29735
UR - https://arxiv.org/abs/2608.29735
AB - Understanding why a target metric changes is a fundamental problem in data-driven decision making, beyond anomaly detection alone. We study root cause attribution for metric changes in complex e-commerce systems, focusing on trade-offs between interpretability, efficiency, and causal validity. As a starting point, we extend a metric-decomposition method into a recursive metric-tree framework for multi-level root cause analysis, but this relies on independence and decomposability assumptions that miss complex causal dependencies. In contrast, graphical causal models (GCMs) relax these assumptions and improve causal validity, at the cost of interpretability, higher computational and data demands, and potential attribution target misalignment. Through real-world applications, mathematical proofs, and simulations, we characterize the fundamental sources of these trade-offs. Guided by these insights, we propose a unified, causally informed attribution approach that integrates structural causal information into the metric-tree decomposition framework and corrects key sources of misalignment in GCM-based causal attributions, substantially improving causal validity while preserving interpretability and fast computation. Analytical proofs and simulations demonstrate that the proposed approach produces more accurate root cause attributions, and we also present a real-world application.
ER -