Now available! Red Hat OpenShift Container Platform for Linux on IBM Z and LinuxONE Learn more

Automate model building with AutoAI

This tutorial is part of the Getting started with IBM Cloud Pak for Data learning path.

With the aim of creating AI for AI, IBM introduced a service on Watson™ Studio called AutoAI.

AutoAI is a service that automates machine learning tasks to ease the tasks of data scientists. It automatically prepares your data for modeling, chooses the best algorithm for your problem, and creates pipelines for the trained models.

AutoAI can be run in public clouds and in private clouds, including IBM Cloud Pak for Data.

Learning objectives

This tutorial explains the benefits of the AutoAI service on a use case. This will give you a better understanding of how regression and classification problems can be handled without any code–and how the tasks (feature engineering, model selection, hyperparameter tuning, etc.) are done with this service. This tutorial also includes details for choosing the best model among the pipelines and how to deploy and use these models via IBM Cloud Pak for Data platform.


Estimated time

This tutorial should take approximately 20 minutes to complete (including the training in AutoAI).

This tutorial is broken up into the following steps:

  1. Create a Project and AutoAI instance
  2. Set up your AutoAI environment and generate pipelines
  3. AutoAI pipeline
  4. Deploy and test the model

1. Create a Project and AutoAI instance

Create a Watson Studio project

  • Click the (☰) hamburger menu in the upper left corner and click Projects. From the Projects page, click New Project:

Create project

  • Select Create an empty project:

Create empty project

  • Give your project, give a name and optional description:

Name your project

The data assets page opens and is where your project assets are stored and organized. By clicking the Assets bar, you can load your dataset from the interface on the right.

Upload dataset

2. Set up your AutoAI environment and generate pipelines

  • To start the AutoAI experience, click Add to Project from the top and select AutoAI:

Adding a project

  • Name your service and choose one of the compute configuration options listed with a drop-down menu. Then, click Create:

Naming your services

  • Select your dataset.

  • Under Select prediction column click Churn. Then click > Run experiment:

Choose Churn column and run

  • The AutoAI experiment will run. The UI will show progress:

autoai progress

  • The experiment will take approximately 14 minutes. Upon completion you will see a message that the pipelines have been created:

autoai pipelines created

3. AutoAI pipeline

The experiment begins just after you complete the previous processes. The AutoAI process follows this sequence to build candidate pipelines:

  • Data pre-processing
  • Automated model selection (Pipeline 1)
  • Hyperparameter optimization (Pipeline 2)
  • Automated feature engineering (Pipeline 3)
  • Hyperparameter optimization (Pipeline 4)

  • Scroll down to see the Pipeline leaderboard:

pipeline leaderboard

The next step is to select the model that gives the best result by looking at the metrics. In this case, Pipeline 4 gave the best result with the metric “Area under the ROC Curve (ROC AUC).” You can view the detailed results by clicking the corresponding pipeline from the leaderboard.

  • Save your model by clicking Save as model and then Save.

Model evaluation

A window opens that asks for the model name, description (optional), and so on. After completing this fields, click Save:

Save model name

You receive a notification to indicate that your model is saved to your project. Click View in project:

Model notification

Alternately, at the top level project under the Assets tab, click the name of your saved model under Models:

choose AI model

4. Deploy and test the model

  • To prepare the model for deployment click Promote to deployment space:

Deploying the model

  • To promote an asset, you must associate your project with a deployment space. Click Associate Deployment Space:

Associate Deployment Space

  • You may have already created a deployment space. In that case, click on Existing and choose that deployment.

  • If you do not have an existing deployment, go to New tab, and give a name for your deployment space, then click Associate.

Create Deployment Space

  • After you promote the model to the deployment space succesfully, a notification will pop-up on the top as below. Click deployment space from this notification. Also you can reach this page by using the (☰) hamburger menu and click Analyze -> Analytics deployments:

deployment space

Menu analytics deployments

  • If you came in through the Menu -> Analyze -> Analytics deployments path, Click on your deployment space:

click deployment space

  • Under the Assets tab, click on your model:

click model in deployment space

  • Under the Deployments tab, click Deploy to deploy this model:

click deploy button

  • Give your deployment an name and optional description and click Create:

create deployment

  • The Deployment will show as In progress and then switch to Deployed when done. Click on the deployment:

click final deployment

  • The Deployment API reference tab show how to use the model using cURL, Java, Javascript, Python, and Scala:

Deployment API reference

Testing the deployed model with the GUI tool

Now you can test your model from the interface that is provided after the deployment.

  • Click on the Input with JSON format icon and paste the following data under Body, then click Predict:
   { "input_data":[ { "fields":[ "customerID", "gender", "SeniorCitizen", "Partner", "Dependents", "tenure", "PhoneService", "MultipleLines", "InternetService", "OnlineSecurity", "OnlineBackup", "DeviceProtection", "TechSupport", "StreamingTV", "StreamingMovies", "Contract", "PaperlessBilling", "PaymentMethod", "MonthlyCharges", "TotalCharges" ],
     "values":[ [ "7567-VHVEG", "Female", 0, "No", "No", 0, "No", "No phone service", "DSL", "No", "No", "Yes", "No", "No", "Yes", "Month-to-month", "No", "Bank transfer (automatic)", 85.25, 85.25 ] ] } ] }

Test deployment with JSON

  • Alternately, you can click the Provide input using form icon and input the various fields, then click Predict:

Input to the fields

Test the deployed model with cURL

NOTE: Windows users will need the cURL command. It’s recommended to download gitbash for this, as you’ll also have other tools and you’ll be able to easily use the shell environment variables in the following steps.

In a terminal window, run the following to get a token to access the API. Use your CP4D cluster username and password:

curl -k -X GET https://<cluster-url>/v1/preauth/validateAuth -u <username>:<password>

A json string will be returned with a value for “accessToken” that will look similar to this:


Export the “accessToken” part of this response in the terminal window as WML_AUTH_TOKEN. Get the URL from the API reference by copying the Endpoint, and export it as URL:

Model Deployment Endpoint

export WML_AUTH_TOKEN=<value-of-access-token>
export URL=

Now run this curl command from a terminal window:

curl -k -X POST --header 'Content-Type: application/json' --header 'Accept: application/json' --header "Authorization: Bearer  $WML_AUTH_TOKEN" -d '{"input_data": [{"fields": ["customerID","gender","SeniorCitizen","Partner","Dependents","tenure","PhoneService","MultipleLines","InternetService","OnlineSecurity","OnlineBackup","DeviceProtection","TechSupport","StreamingTV","StreamingMovies","Contract","PaperlessBilling","PaymentMethod","MonthlyCharges","TotalCharges"],"values": [["7590-VHVEG","Female",0,"No","No",1,"No","No phone service","DSL","No","No","No","No","No","No","Month-to-month","No","Bank transfer (automatic)",25.25,25.25]]}]}' $URL

A json string will be returned with the response, including a “Yes” of “No” at the end indicating the prediction of if the customer will churn or not.

Damla Altunay
Scott D’Angelo