Don’t call it ML: A New Approach for Troubleshooting with the Elastic Stack

Don’t call it machine learning: A New Approach for Troubleshooting with the Elastic Stack

Doors open at 5 pm and the presentation begins at 5:30 pm. Food, refreshments, and networking to follow!

Please RSVP if you plan on attending!

The All Hands Meeting Room is located in Suite 170 on the first floor.
If you are interested in organizing future meetups, hosting an event, and/or speaking, please reach out to **olivia@elastic.co.**

Can't attend in person? Feel free to tune in and catch the presentation over Zoom starting at 5:30pm PDT - https://us02web.zoom.us/j/88222185574?from=addon

Talk Abstract: A New Machine Learning Approach for Troubleshooting with the Elastic Stack - Rod Bagg, Founder and VP Engineering @ Zebrium
Imagine this: you wake up to find your Slack blowing up. Alerts are going off and users are complaining. You go straight to your monitoring dashboard, and you can see right away there's a problem. What's not clear is the reason: what happened? When you can't tell the root cause from your other canned dashboards and alert rules, you have to go searching through logs. You sink into despair... it's going to be a long night.
In this technical discussion, we'll describe an unsupervised machine learning approach that mimics the process of an experienced troubleshooter. It identifies small clusters of log events that are the best indicators of root cause. The resultant payload is summarized using NLP and sent with relevant metrics to Elasticsearch for visualization alongside other observability data on any Kibana dashboard. Rod Bagg, Founder and VP Engineering, will describe and demo the machine learning technology together with feedback from real-world users.

COVID Protocols: TBD - Please check back as we will update this section with guidelines according to local policies.