AIOps Essentials: Issue Detection using Anomaly Detection on top of APM | AIOps Use Cases (3/5)

Artificial intelligence for IT operations (AIOps) is a way to automate tasks that are typically carried out by site reliability engineers (SREs). It aims to make the lives of SREs easier by helping them reduce the amount of noise coming from systems, surface issues more easily, and perform root cause analysis by correlating data from different systems

In this video, we explore using machine learning on top of data that we've already collected. Specifically, we focus on issue detection using unsupervised machine learning. We demonstrate how Elastic can both reduce noise and focus on important data, as well as detect normal or abnormal system behavior without prior knowledge of what "normal" or "good" state is. We also show how to create machine learning jobs and use anomaly detection in the APM to analyze data from microservices, system calls, and Kubernetes.

Chapters:
00:00 - Issue Detection introduction
03:00 - Anomaly Detection for APM
08:20 - Anomaly Detection for Hosts (Kubernetes)
12:54 - Anomaly Explorer
18:42 - Creating business metrics from logs
29:00 - Anomaly Detection on Business Metrics
31:46 - Issue detection on processed payments
34:00 - Forecast

Additional Resources:

Connect with us on social media:

About Elastic
Elastic, the Search AI Company, enables everyone to find the answers they need in real time, using all their data, at scale. Elastic’s solutions for search, observability, and security are built on the Elastic Search AI Platform — the development platform used by thousands of companies, including more than 50% of the Fortune 500.

#AIOps #Observability #DevOps #ElasticObservability #MachineLearning #DataAnalysis #IssueDetection #UnsupervisedLearning #APM #Microservices #Kubernetes #AnomalyDetection #opentelemetry