In this topic, a binary classification model is used as an example to describe how to evaluate models.

Prerequisites

Algorithm modeling is complete. For more information, see Algorithm modeling.

Procedure

  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. Drag and drop components onto the canvas to create an experiment.
    1. In the left-side navigation pane, click Components.
    2. In the Components list, choose Machine Learning > Recommendation. Then, drag and drop the Prediction component onto the canvas.
    3. In the Components list, choose Machine Learning > Evaluation. Then, drag and drop the Binary Classification Evaluation component onto the canvas, and connect it to the components prepared during Algorithm modeling. The following figure shows how to connect the components.Model evaluation
    4. Click the Binary Classification Evaluation component on the canvas. On the uicontrol Fields Setting tab on the right side, set the Original Label Column to ifhealth.
  5. On the top of the canvas, click Run.
  6. View the model evaluation result.
    1. After the experiment stops running, right-click the Binary Classification Evaluation component. In the menu that appears, click View Evaluation Report.
    2. Click the Charts tab, and view the receiver operating characteristic curve (ROC) of the binary classification model with different parameters.Model evaluation