Elasticsearch Machine Learning Architecture and Requirements

Elastic Stack Elasticsearch
1

Hi,

I'm looking into integrating machine learning capabilities with Elasticsearch and have a few questions regarding architectural considerations and prerequisites for ML features.

1.Architectural Placement of ML Components:
How are machine learning components typically integrated into an Elasticsearch architecture? What's a general guideline for the ratio of ML nodes to Elasticsearch data nodes?

2.Prerequisites for Anomaly Detection and Root Cause Analysis:
What are the necessary prerequisites and configurations for utilizing ML features like anomaly detection and root cause analysis in Elasticsearch?

Are there any official Elastic documentation or best practice guides that address these specific questions?

Thanks.

2

Hi @Wei_Li, and thanks for exploring Elasticsearch ML features.

I'm sure someone with more expertise will respond soon, but in the meantime, here are some Elastic docs that might be helpful:

Setting up machine learning

Working with anomaly detection at scale

Anomaly detection how-tos and blog posts

Machine learning settings in Elasticsearch

Hope these help as a starting point.