In this topic, the heart disease prediction template is used as an example to describe how to create experiments and deploy experiment models.


  • You have purchased services of Machine Learning Platform for AI. For more information, see Purchase.
  • A project is created. For more information, see Create a project.


  1. Log on to the Machine Learning Platform for AI console.
  2. In the left-side navigation pane, choose Model Training > Studio-Modeling Visualization, and navigate to the PAI Visualization Modeling page.
  3. Click Machine Learning.Machine learning
  4. Create and run an experiment.
    1. In the left-side navigation pane, click Home.
    2. In the Templates section, find the Heart Disease Prediction template, and click Create.
    3. In the New Experiment dialog box, enter a name in the Name field, and click OK.
    4. The experiment is created after about 10 seconds. The following figure shows the created experiment.Experiment of heart disease prediction
    5. On the top of the canvas, click Run. When the experiment is running, right-click the components to view their output information.
  5. Deploy the model.
    1. After the experiment stops running, move the pointer over Deploy, and click Online Model Service.
    2. Click Next, and enter the Resources And Models page.
    3. Enter a name in the Custom Model Name field, and keep the default settings for the other parameters.
    4. Click Deploy.
    5. When the status of the model changes from Creating to Running in the State column, the model is deployed.
      Note When the model is unused, click Stop in the Operating column. This saves costs.