---
title: Schedule recurring batch prediction jobs
description: How to configure, execute, and schedule batch prediction jobs for deployed models.

---

# Schedule recurring batch prediction jobs {: #schedule-recurring-batch-prediction-jobs }

You might want to make a [one-time batch prediction](batch-pred), but you might also want to schedule regular batch prediction jobs. This section shows how to create and schedule batch prediction jobs.

Be sure to review the [deployment and prediction considerations](deployment/index#feature-considerations) before proceeding.

## Create a prediction job definition {: #create-a-prediction-job-definition }

Job definitions are flexible templates for creating batch prediction jobs. You can store definitions inside DataRobot and run new jobs with a single click, API call, or automatically via a schedule. Scheduled jobs do not require you to provide connection, authentication, and prediction options for each request.

To create a job definition for a deployment, navigate to the **Job Definitions** tab. The following table describes the information and actions available on the **New Prediction Job Definition** tab.

![](images/prediction-job-description-simplify.png)

| | Field name |  Description  |
|---|---------------------|--------------|
| ![](images/icon-1.png) | Prediction job definition name | Enter the name of the prediction job that you are creating for the deployment. |
| ![](images/icon-2.png) | Prediction source | Set the [source type](#set-up-prediction-sources) and [define the connection](data-conn) for the data to be scored.  |
| ![](images/icon-3.png) |  Prediction options | [Configure the prediction options](#set-prediction-options). |
| ![](images/icon-4.png) | Time series options | Specify and configure a [time series prediction method](#set-time-series-options).  |
| ![](images/icon-5.png) | Prediction destination | Indicate the output destination for predictions. Set the [destination type](#set-up-prediction-destinations) and [define the connection](data-conn). |
| ![](images/icon-6.png) | Jobs schedule | Toggle whether to run the job immediately and whether to [schedule the job](#schedule-prediction-jobs).|
| ![](images/icon-7.png) | Save prediction job definition | Click this button to save the job definition. The button changes to **Save and run prediction job definition** if the **Run this job immediately** toggle is turned on. Note that this button is disabled if there are validation errors.  |

Once fully configured, click **Save prediction job definition** (or **Save and run prediction job definition** if **Run this job immediately** is enabled).

!!! note
    Completing the **New Prediction Job Definition** tab configures the details required by the Batch Prediction API. Reference the [Batch Prediction API](batch-prediction-api/index) documentation for details.

## Set up prediction sources {: #set-up-prediction-sources }

Select a prediction source (also called an [intake adapter](intake-options)):

![](images/prediction-job-description-source.png)

To set a prediction source, complete the appropriate authentication workflow for the [source type](#source-connection-types). 

For AI Catalog sources, the job definition displays the modification date, the user that set the source, and a [badge](http://datarobot-docs.hq.datarobot.com/3317/en/html/data/import-data/catalog-asset.html#asset-states) that represents the state of the asset (in this case, STATIC). 

After you set your prediction source, DataRobot validates that the data is applicable for the deployed model:

![](images/prediction-job-description-source-validation.png)

!!! note
    DataRobot validates that a data source is applicable with the deployed model when possible but not in all cases. DataRobot validates for AI Catalog, most JDBC connections, Snowflake, and Synapse.
   

### Source connection types {: #source-connection-types }

Select a connection type below to view field descriptions.

!!! note
    When browsing for connections, invalid adapters are not shown.

**Database connections**

* [JDBC](intake-options#jdbc-scoring)
    
**Cloud Storage Connections**
    
* [Azure](intake-options#azure-blob-storage-scoring)
* [Google Cloud Storage](intake-options#google-cloud-storage-scoring) (GCP Cloud)
* [S3](intake-options#s3-scoring)

**Data Warehouse Connections**

* [BigQuery](intake-options#bigquery-scoring)
* [Snowflake](intake-options#snowflake-scoring)
* [Synapse](intake-options#synapse-scoring)

**Other**

* [AI Catalog](intake-options#ai-catalog-dataset-scoring)  

For information about supported data sources, see [Data sources supported for batch predictions](batch-prediction-api/index#data-sources-supported-for-batch-predictions).


## Set prediction options {: #set-prediction-options }

Specify what information to include in the prediction results:

{% include 'includes/prediction-options-include.md' %}
     
## Set time series options {: #set-time-series-options }

{% include 'includes/batch-pred-ts-scoring-data-requirements.md' %}

{% include 'includes/batch-pred-jobs-ts-options-include.md' %}

## Set up prediction destinations {: #set-up-prediction-destinations }

Select a prediction destination (also called an [output adapter](output-options)):

![](images/prediction-job-description-destination.png)

Complete the appropriate authentication workflow for the [destination type](#source-connection-types).

### Destination connection types {: #destination-connection-types }

Select a connection type below to view field descriptions.

!!! note
    When browsing for connections, invalid adapters are not shown.

**Database connections**

* [JDBC](output-options#jdbc-write)
    
**Cloud Storage Connections**
    
* [Azure](output-options#azure-blob-storage-write)
* [Google Cloud Storage](output-options#google-cloud-storage-write) (GCP Cloud)
* [S3](output-options#s3-write)

**Data Warehouse Connections**

* [BigQuery](output-options#bigquery-write)
* [Snowflake](output-options#snowflake-write)
* [Synapse](output-options#synapse-write)

**Other**

* [Tableau](output-options#tableau-write)  

## Schedule prediction jobs {: #schedule-prediction-jobs }

You can schedule prediction jobs to run automatically on a schedule. When outlining a job definition, toggle the jobs schedule on. Specify the frequency (daily, hourly, monthly, etc.) and time of day to define the schedule on which the job runs.

![](images/batch-7.png)

For further granularity, select **Use advanced scheduler**. You can specify the exact time for the prediction job to run down to the minute.

![](images/batch-8.png)

After setting all applicable options, click **Save prediction job definition**.