Skip to content

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

Deploy a DataRobot model in a DataRobot environment

DataRobot AutoML models allow you to deploy to a DataRobot-managed prediction environment. This deployment method is the most direct route to making predictions and monitoring, managing, and governing your model in a centralized deployment hub.

To create and deploy an AutoML model on DataRobot, follow the workflow outlined below:

graph TB
  A{Deployment method?} --> |Leaderboard|B[Deploy a model from the Leaderboard]:::link;
  classDef link color: blue;
  click B "./dr-model-dr-env.html#deploy-a-model-from-the-leaderboard"
  A --> |Model registry|C[Register a model]:::link
  click C "./dr-model-dr-env.html#register-a-model"
  C --> D[Deploy a model from the Model Registry]:::link
  click D "./dr-model-dr-env.html#deploy-a-model-from-the-model-registry"

Deploy a model from the Leaderboard

DataRobot AutoML automatically generates models and displays them on the Leaderboard. The model recommended for deployment appears at the top of the page. You can deploy this (or any other) model directly from the Leaderboard to start making and monitoring predictions. When you create a deployment from a model, DataRobot automatically creates a model package for the deployed model. You can access the model package at any time in the Model Registry.

Deploy from the Leaderboard

Register a model

If you don't want to deploy immediately from the Leaderboard, you can add a model package to the Model Registry to deploy later.

Note

This method allows you to share a model package or generate compliance documentation before deploying a model.

Register a model

Deploy a model from the Model Registry

After you've added a model to the Model Registry, you can deploy it at any time to start making and monitoring predictions.

Deploy from the Model Registry


Updated June 22, 2022
Back to top