Machine learning
editMachine learning
edit[preview] This functionality is in technical preview and may be changed or removed in a future release. Elastic will work to fix any issues, but features in technical preview are not subject to the support SLA of official GA features.
This content applies to: 
To view your machine learning resources, go to Project settings → Management → Machine Learning:
The machine learning features that are available vary by project type:
- Elasticsearch Serverless projects have trained models.
- Observability projects have anomaly detection jobs.
- Elastic Security projects have anomaly detection jobs, data frame analytics jobs, and trained models.
For more information, go to Anomaly detection, Data frame analytics and Natural language processing.
Synchronize saved objects
editBefore you can view your machine learning datafeeds, jobs, and trained models in Kibana, they must have saved objects. For example, if you used APIs to create your jobs, wait for automatic synchronization or go to the Machine Learning page and click Synchronize saved objects.
Export and import jobs
editYou can export and import your machine learning job and datafeed configuration details on the Machine Learning page. For example, you can export jobs from your test environment and import them in your production environment.
The exported file contains configuration details; it does not contain the machine learning models. For anomaly detection, you must import and run the job to build a model that is accurate for the new environment. For data frame analytics, trained models are portable; you can import the job then transfer the model to the new cluster. Refer to Exporting and importing data frame analytics trained models.
There are some additional actions that you must take before you can successfully import and run your jobs:
- The data views that are used by anomaly detection datafeeds and data frame analytics source indices must exist; otherwise, the import fails.
- If your anomaly detection jobs use custom rules with filter lists, the filter lists must exist; otherwise, the import fails.
- If your anomaly detection jobs were associated with calendars, you must create the calendar in the new environment and add your imported jobs to the calendar.