Autonomous Log Monitoring: Using machine learning for auto incident detection

Speaker: Larry Lancaster - Founder and CTO @ Zebrium

Abstract:
We use logs to root cause software incidents, so why aren't they the ultimate source for detecting these incidents? Log monitoring is stuck in the human-driven "index-and-search" paradigm of 20 years ago. Searching and poking around logs is slow, "dumb" alert rules cause alert fatigue, and smarter alert rules are fragile.

Speaker Bio:
Larry Lancaster is the founder and CTO of Zebrium. He started Zebrium with the vision that machine learning could be used to automatically detect software incidents by structuring and learning patterns in logs and metrics. Before Zebrium, Larry was Chief Data Scientist at Nimble Storage, founding that company's data science team and architecting/implementing their peta-scale platform for automation and analytics. He also started NetApp's Engineering Informatics Group as Senior Engineer, invented Glassbeam's ETL-focused SPL technology as CTO/Co-Founder, and received a leadership award from the International Congress on Neural Networks as graduate student.

The future of log monitoring can't remain stuck in the manual "index-and-search" world - it must be autonomous! Learn about and see a demo of an approach that uses unsupervised machine learning to automatically detect and help find the root cause of incidents.
Our meetings are scheduled for 7:30pm on the third Thursday of each month.

BayLISA includes system and network administrators across a range of skill levels. BayLISA meets to discuss topics of interest to system administrators and managers. The meetings are free and open to the public.

We always welcome presentation topics and volunteer speakers. Use the "Contact us" link on this page to get in touch with BayLISA's directors.