WARNING: Version 6.1 of the Elastic Stack has passed its EOL date.
This documentation is no longer being maintained and may be removed. If you are running this version, we strongly advise you to upgrade. For the latest information, see the current release documentation.
Machine learning jobs contain the configuration information and metadata necessary to perform an analytics task.
Each job has one or more detectors. A detector applies an analytical function to specific fields in your data. For more information about the types of analysis you can perform, see Function Reference.
A job can also contain properties that affect which types of entities or events are considered anomalous. For example, you can specify whether entities are analyzed relative to their own previous behavior or relative to other entities in a population. There are also multiple options for splitting the data into categories and partitions. Some of these more advanced job configurations are described in the following section: Configuring Machine Learning.
For a description of all the job properties, see Job Resources.
In Kibana, there are wizards that help you create specific types of jobs, such as single metric, multi-metric, and population jobs. A single metric job is just a job with a single detector and limited job properties. To have access to all of the job properties in Kibana, you must choose the advanced job wizard. If you want to try creating single and multi-metrics jobs in Kibana with sample data, see Getting Started.
You can also optionally assign jobs to one or more job groups. You can use job groups to view the results from multiple jobs more easily and to expedite administrative tasks by opening or closing multiple jobs at once.