Machine Data Analytics
When analyzing machine data, modern enterprises consistently face challenges revolving around the human limitation in knowing what to ask of the data. Many organizations do not recognize that there are two types of machine data analytics, and that distinguishing between the two is essential for successful troubleshooting and monitoring of your IT infrastructure:
- Analyzing and answering questions you know to ask about your infrastructure. This is the “known unknowns” problem, the resolution to which involves functions like iterative search, alerting, reporting and dashboard visualization.
- Gaining insights even when you don't know what questions to ask -- the “unknown unknowns” problem. Fundamentally people can’t glean insights from machine data when they don’t know where to look or what to look for. The difficult “unknown unknowns” problem is where machine learning comes in, as only modern machine data science, with automated, algorithm-driven predictive analytics, can reach beyond human limitations to extract insights from massive volumes of Big Data.
Sumo Logic focuses on combining the best of human-based interactions (searches, alerts, dashboards, etc.) with machine learning (LogReduce, Anomaly Detection) to enable enterprises to succeed in both types of machine data analytics. In doing so, the Sumo Logic service provides insights from machine data to satisfy both business and operational requirements.
Sumo Logic Anomaly Detection leverages machine learning to enable enterprises to extend beyond the human limitation of pre-defined rules and reports. Built on top of the pattern-recognition capabilities of LogReduce, Anomaly Detection automatically detects anomalies in streams of machine data and then assembles these anomalies into events. By identifying and investigating these unknown events, enterprises can generate previously undiscoverable insights across their entire IT infrastructure.
The patent-pending LogReduce technology is capable of reducing hundreds of thousands of pages of query results into a single page of meaningful patterns. Leveraging powerful machine-learning algorithms, LogReduce sifts through the noise of log data and surfaces meaningful patterns and behaviors that significantly shorten the time companies take to identify and fix the root cause of issues.