Skip to content

Click in-app to access the full platform documentation for your version of DataRobot.

Deploy DataRobot models

You can deploy models you build with DataRobot AutoML using the following methods:

Tip

In most cases, before deployment, you should unlock holdout and retrain your model at 100% to improve predictive accuracy. DataRobot automatically runs Feature Impact for the model (this also calculates Prediction Explanations, if available).

Deploy from the Leaderboard

To create a deployment from the Leaderboard:

  1. From the Leaderboard, select the model to use for generating predictions and click Predict > Deploy. The Deploy model page lets you create a new deployment for the selected model. In this example, the model is both recommended for deployment and prepared for deployment:

    Note

    The Deploy tab behaves differently in environments without a dedicated prediction server, as described in the section on shared modeling workers, below.

  2. If the model is not prepared for deployment as in the example below, best practice recommends that you click Prepare for deployment. DataRobot runs feature impact, retrains the model on a reduced feature list, trains on a higher sample size and then the full sample size (latest data for date/time partitioned projects).

  3. If using a binary classification model, set the Prediction threshold before proceeding. (New models added to the Leaderboard are assigned the default value 0.5.)

    Note

    If you set the prediction threshold before the deployment preparation process, the value does not persist through the process. When deploying the prepared model, if you want it to use a value other than the default, set the value after the model has the Prepared for Deployment badge applied.

  4. To deploy a prepared model, click Deploy model.

  5. Add deployment information and create the deployment.

Deploy from the Model Registry

  1. Navigate to Model Registry > Model Packages.

  2. Select Deploy from the action menu for the model package you wish to deploy.

  3. Add deployment information and create the deployment.

Use shared modeling workers

If you don't have a dedicated prediction server instance available, you can use a node that shares workers with your model building activities. In this case, the page has a different interface.

Click Show Example to generate and display a usage example:

When using the sample code, specify your API key (1). The project and model IDs (2) are available in the sample, as is the shared instance endpoint (3). The DataRobot Python client uses the API key for authentication and so no key or username is required. To execute the file, follow the instructions in the commented section of the snippet.


Updated May 25, 2023
Back to top