Robust anomaly detection for real-world user monitoring data – Velocity 2016, Santa Clara, CA

Robust anomaly detection for real-world user monitoring data – Velocity 2016, Santa Clara, CA

Home › Ritesh Maheshwari › Robust anomaly detection for real-world user monitoring data – Velocity 2016, Santa Clara, CA
Ritesh Maheshwari • Available on Youtube • Published 8 years ago
Robust anomaly detection for real-world user monitoring data – Velocity 2016, Santa Clara, CA
ChannelPublish DateThumbnail & View CountDownload Video
Channel AvatarPublish Date not found Thumbnail
0 Views
View on YouTube Download Video
Code: https://github.com/linkedin/luminol

Over the past year, LinkedIn has deployed and incrementally improved Luminol, its anomaly detection system that detects anomalies in Real User Monitoring (RUM) data for LinkedIn pages and apps. Ritesh Maheshwari and Yang Yang provide an overview of Luminol, focusing on building a low-cost, end-to-end system that can leverage any algorithm, and share lessons learned and best practices that are useful for any engineering or operations team. LinkedIn will open source its Python anomaly detection and correlation library during the talk.

Topics include:

use cases
How to avoid an alarm black hole
Data processing
Overview of Luminol
Cause identification
Alarm
Success stories

Please take the opportunity to connect with your friends and family and share this video with them if you find it useful.