Analyzing Operational Data at Scale Using ML at Intuit

Explore a conference talk that delves into Intuit's approach to analyzing operational data at scale using machine learning. Learn how the company manages approximately 2000 services in pre-production and production environments on Kubernetes, implementing an efficient system for problem detection and isolation through automated analysis of operational data. Discover the intricacies of Intuit's Operational Data Lake, built using stream processing and efficient data structures and cache, which serves as a warehouse for clean, documented, and schematized operational data from various cloud infrastructure, Kubernetes, and application events and metrics. Gain insights into the application of simple machine learning techniques for automatic anomaly detection in impacted services and causal service identification. Witness a demonstration of how this system aids in swift detection and identification of production issues, enhancing overall operational efficiency.

Analyzing Operational Data at Scale Using ML at Intuit - Amit Kalamkar & Vigith Maurice, Intuit