AI-Ops

AI-Ops, short for Artificial Intelligence for IT Operations, represents a transformative approach to managing and optimizing complex IT environments. In today’s rapidly evolving digital landscape, organizations are faced with the daunting challenge of maintaining the reliability and efficiency of their IT systems. AI-Ops leverages cutting-edge artificial intelligence and machine learning technologies to autonomously monitor, analyze, and optimize IT infrastructure, from servers and networks to applications and data. By harnessing the power of AI, AI-Ops not only enhances the agility and responsiveness of IT operations but also anticipates and proactively addresses issues, reducing downtime, improving performance, and ultimately empowering organizations to thrive in the age of digital transformation.

Ongoing Research

We currently work on multiple topics in this area:

• Log Analytics
• Failure Localization and Diagnosis
• AIOps Systems

Featured Publications

• AmocRCA: At Most One Change Segmentation and Relative Correlation Ranking for Root Cause Analysis
  Anton Altenbernd, Wu Zhiyuan, Odej Kao.
  Companion of the ACM International Conference on the Foundations of Software Engineering (FSE). 2025. [find it here]
• A2Log: Attentive Augmented Log Anomaly Detection
  Thorsten Wittkopp, Alexander Acker, Sasho Nedelkoski, Jasmin Bogatinovski, Dominik Scheinert, Wu Fan, Odej Kao
  Proceedings of the 55th Hawaii International Conference on System Sciences. 2022. [read here]
• Self-attentive Classification-based Anomaly Detection in Unstructured Logs
  Sasho Nedelkoski, Jasmin Bogatinovski, Alexander Acker, Jorge Cardoso, Odej Kao
  IEEE International Conference on Data Mining 2020. [read here]
• Failure Identification from Unstable Log Data using Deep Learning
  Jasmin Bogatinovski, Sasho Nedelkoski, Li Wu, Jorge Cardoso, Odej Kao
  IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID) 2022. [read here]
• MicroRCA: Root Cause Localization of Performance Issues in Microservices
  Li Wu, Johan Tordsson, Erik Elmroth, Odej Kao
  NOMS 2020 IEEE/IFIP Network Operations and Management Symposium, pages 1–9. IEEE, 2020. [read here]