34 lines
1.6 KiB
Plaintext
34 lines
1.6 KiB
Plaintext
[[ml-jobs]]
|
|
=== Machine Learning Jobs
|
|
++++
|
|
<titleabbrev>Jobs</titleabbrev>
|
|
++++
|
|
|
|
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 <<ml-functions>>.
|
|
|
|
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: <<ml-configuring>>.
|
|
|
|
For a description of all the job properties, see
|
|
{ref}/ml-job-resource.html[Job Resources].
|
|
|
|
In {kib}, 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 {kib}, you must choose the _advanced_ job wizard.
|
|
If you want to try creating single and multi-metrics jobs in {kib} with sample
|
|
data, see <<ml-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.
|