AI + Network Papers16 min read12 citations

Causal Inference for Root Cause Analysis in Autonomous Networks

Dr. Fatemeh Ghassemi, Prof. Mung Chiang

Purdue University

Feb 7, 2026View on arXiv

Abstract

We apply causal inference methods to network root cause analysis, moving beyond correlational ML approaches that often mislead. Our causal discovery algorithm constructs a directed acyclic graph of KPI dependencies from observational network data, enabling identification of true root causes rather than symptoms. On a dataset from a tier-1 operator with 10,000 fault incidents, causal analysis correctly identifies root causes in 88% of cases, compared to 62% for correlation-based methods.

AI Summary

AI-Generated Summary
  • Causal inference applied to network root cause analysis.
  • 88% root cause identification accuracy vs 62% for correlation-based methods.
  • Constructs causal DAG of KPI dependencies from observational data.
  • Validated on 10,000 real fault incidents from a tier-1 operator.

Key Findings

  • 1Correlation-based methods misidentify symptoms as causes in 30% of cases.
  • 2Causal graphs reveal hidden dependencies between seemingly unrelated KPIs.
  • 3The approach works with observational data without requiring controlled experiments.

Industry Implications

Enables truly autonomous fault management in 6G networks.

Reduces MTTR by identifying actual causes rather than correlated symptoms.

Builds a causal knowledge base that improves with each incident.

Causal InferenceRoot Cause AnalysisAutonomous NetworksFault Management

Read the Original Paper

Access the full paper on arXiv for complete methodology, results, and references.

Open on arXiv

Related Papers