# Actionable and Interpretable Fault Localization for Recurring Failures in Online Service Systems

arXiv: https://arxiv.org/abs/2207.09021 · HTML: https://mlsanity.com/paper/2207.09021/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2022.

## Built on by (most cited first, 19 of 19)

- [Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysis](https://mlsanity.com/paper/2502.08224/) (2025)
- [D-Bot: Database Diagnosis System using Large Language Models](https://mlsanity.com/paper/2312.01454/) (2023)
- [Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems](https://mlsanity.com/paper/2603.00468/) (2026)
- [TAMO: Fine-Grained Root Cause Analysis via Tool-Assisted LLM Agent with Multi-Modality Observation Data in Cloud-Native Systems](https://mlsanity.com/paper/2504.20462/) (2025)
- [A Comprehensive Survey on Root Cause Analysis in (Micro) Services: Methodologies, Challenges, and Trends](https://mlsanity.com/paper/2408.00803/) (2024)
- [The Multi-Agent Fault Localization System Based on Monte Carlo Tree Search Approach](https://mlsanity.com/paper/2507.22800/) (2025)
- [OpsAgent: An Evolving Multi-agent System for Incident Management in Microservices](https://mlsanity.com/paper/2510.24145/) (2025)
- [GAL-MAD: Towards Explainable Anomaly Detection in Microservice Applications Using Graph Attention Networks](https://mlsanity.com/paper/2504.00058/) (2025)
- [A Systematic Literature Review on Explainability for Machine/Deep Learning-based Software Engineering Research](https://mlsanity.com/paper/2401.14617/) (2024)
- [FaultProfIT: Hierarchical Fault Profiling of Incident Tickets in Large-scale Cloud Systems](https://mlsanity.com/paper/2402.17583/) (2024)
- [SLIM: a Scalable Light-weight Root Cause Analysis for Imbalanced Data in Microservice](https://mlsanity.com/paper/2405.20848/) (2024)
- [A Scenario-Oriented Benchmark for Assessing AIOps Algorithms in Microservice Management](https://mlsanity.com/paper/2407.14532/) (2024)
- [Root Cause Analysis for Microservice Systems via Cascaded Conditional Learning with Hypergraphs](https://mlsanity.com/paper/2511.17566/) (2025)
- [Generic and Robust Root Cause Localization for Multi-Dimensional Data in Online Service Systems](https://mlsanity.com/paper/2305.03331/) (2023)
- [KGroot: Enhancing Root Cause Analysis through Knowledge Graphs and Graph Convolutional Neural Networks](https://mlsanity.com/paper/2402.13264/) (2024)
- [Root Cause Analysis Method Based on Large Language Models with Residual Connection Structures](https://mlsanity.com/paper/2602.08804/) (2026)
- [UModel: An Agent-Ready Observability Data Modeling Method at Scale](https://mlsanity.com/paper/2606.04799/) (2026)
- [SDVDiag: Multimodal Causal Discovery for Online Diagnosis in Software-defined Vehicles](https://mlsanity.com/paper/2606.15559/) (2026)
- [STAR: Adaptive Spatial-Temporal Normalization for Unified Microservice Incident Management](https://mlsanity.com/paper/2609.31645/) (2026)

## Abstract (arXiv)

Fault localization is challenging in an online service system due to its monitoring data's large volume and variety and complex dependencies across or within its components (e.g., services or databases). Furthermore, engineers require fault localization solutions to be actionable and interpretable, which existing research approaches cannot satisfy. Therefore, the common industry practice is that, for a specific online service system, its experienced engineers focus on localization for recurring failures based on the knowledge accumulated about the system and historical failures. Although the above common practice is actionable and interpretable, it is largely manual, thus slow and sometimes inaccurate. In this paper, we aim to automate this practice through machine learning. That is, we propose an actionable and interpretable fault localization approach, DejaVu, for recurring failures in online service systems. For a specific online service system, DejaVu takes historical failures and dependencies in the system as input and trains a localization model offline; for an incoming failure, the trained model online recommends where the failure occurs (i.e., the faulty components) and which kind of failure occurs (i.e., the indicative group of metrics) (thus actionable), which are further interpreted by both global and local interpretation methods (thus interpretable). Based on the evaluation on 601 failures from three production systems and one open-source benchmark, in less than one second, DejaVu can on average rank the ground truths at 1.66-th to 5.03-th among a long candidate list, outperforming baselines by at least 51.51%.