CCA: An ML Pipeline for Cloud Anomaly Troubleshooting


  • Lili Georgieva IBM Research
  • Ioana Giurgiu IBM Research
  • Serge Monney IBM
  • Haris Pozidis IBM Research
  • Viviane Potocnik IBM Research
  • Mitch Gusat IBM Research



Causality, Explainability, Timeseries, Cloud


Cloud Causality Analyzer (CCA) is an ML-based analytical pipeline to automate the tedious process of Root Cause Analysis (RCA) of Cloud IT events. The 3-stage pipeline is composed of 9 functional modules, including dimensionality reduction (feature engineering, selection and compression), embedded anomaly detection, and an ensemble of 3 custom explainability and causality models for Cloud Key Performance Indicators (KPI). Our challenge is: How to apply a reduced (sub)set of judiciously selected KPIs to detect Cloud performance anomalies, and their respective root causal culprits, all without compromising accuracy?




How to Cite

Georgieva, L., Giurgiu, I., Monney, S., Pozidis, H., Potocnik, V., & Gusat, M. (2022). CCA: An ML Pipeline for Cloud Anomaly Troubleshooting. Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 13167-13169.