Skip to main content

Task 6: Interpret built model

To delve deeper into the time series model we've constructed, let's utilize the INTERPRET THIS MODEL button in H2O Driverless AI to generate an MLI report. This functionality is particularly valuable for enhancing machine learning interpretability, especially in regulated industries where transparency and explanation are crucial. You can interpret the model by using the generated MLI report. As a result, you can uncover valuable insights into its inner workings, such as feature importance and other performance metrics. This process can empower you to understand better and trust the predictions made by the model.

  1. Click INTERPRET THIS MODEL.
  2. Select WITH DEFAULT SETTINGS. interpret the model
  3. Wait a few moments for the MLI report to get generated.

Summary​

Summary tab

The Summary tab provides an overview of the interpretation, including the dataset and Driverless AI experiment name (if available) that were used for the interpretation along with the feature space (original or transformed), target column, problem type, and k-LIME information. If the interpretation was created from a Driverless AI model, then a table with the Driverless AI model summary is also included along with the top variables for the model.

For more information about the Summary tab, see the Summary tab in Tutorial 2A.

DAI model​

DAI model tab

The DAI Model tab is organized into tiles for each interpretation method. To view a specific plot, click the tile for the plot that you want to view.

note

For more detailed information on each plot, see DAI model in Tutorial 4A.

Surrogate models​

The Surrogate model tab is organized into tiles for each interpretation method. To view a specific plot, click the tile for the plot that you want to view.

note

For more detailed information on each plot, see Surrogate model in Tutorial 4A.

Now that you’ve learned how to interpret the model using the generated MLI report, in Task 7, you’ll learn how to deploy the generated NLP model with H2O MLOps.

Feedback