- Machine Learning: other versions:
- What is Elastic Machine Learning?
- Setup and security
- Anomaly detection
- Finding anomalies
- Tutorial: Getting started with anomaly detection
- Advanced concepts
- API quick reference
- How-tos
- Generating alerts for anomaly detection jobs
- Aggregating data for faster performance
- Altering data in your datafeed with runtime fields
- Customizing detectors with custom rules
- Detecting anomalous categories of data
- Reverting to a model snapshot
- Detecting anomalous locations in geographic data
- Mapping anomalies by location
- Adding custom URLs to machine learning results
- Anomaly detection jobs from visualizations
- Exporting and importing machine learning jobs
- Resources
- Data frame analytics
- Natural language processing
Supplied anomaly detection configurations
editSupplied anomaly detection configurations
editAnomaly detection jobs contain the configuration information and metadata necessary to perform an analytics task. Kibana can recognize certain types of data and provide specialized wizards for that context. This page lists the categories of the anomaly detection jobs that are ready to use via Kibana in Machine learning. Refer to Create anomaly detection jobs to learn more about creating a job by using supplied configurations. Logs and Metrics supplied configurations are available and can be created via the related solution UI in Kibana.
The configurations are only available if data exists that matches the queries specified in the manifest files. These recognizer queries are linked in the descriptions of the individual configurations.
Model memory considerations
editBy default, these jobs have model_memory_limit
values that are deemed
appropriate for typical user environments and data characteristics. If your
environment or your data is atypical and your jobs reach a memory status value
of soft_limit
or hard_limit
, you might need to update the model memory
limits. For more information, see
Working with anomaly detection at scale.
On this page