Configuring Machine Learning

If you want to use X-Pack machine learning features, there must be at least one machine learning node in your cluster and all master-eligible nodes must have machine learning enabled. By default, when you install X-Pack, all nodes are machine learning nodes. For more information about these settings, see X-Pack Settings.

To use the X-Pack machine learning features to analyze your data, you must create a job and send your data to that job.

  • If your data is stored in Elasticsearch:

    • You can create a datafeed, which retrieves data from Elasticsearch for analysis.
    • You can use Kibana to expedite the creation of jobs and datafeeds.
  • If your data is not stored in Elasticsearch, you can POST data from any source directly to an API.

The results of machine learning analysis are stored in Elasticsearch and you can use Kibana to help you visualize and explore the results.

For a tutorial that walks you through these configuration steps, see Getting Started.

Though it is quite simple to analyze your data and provide quick machine learning results, gaining deep insights might require some additional planning and configuration. The scenarios in this section describe some best practices for generating useful machine learning results and insights from your data.