Skip to main content

Task 6: Summary tab

Overview​

In the MLI (Machine Learning Interpretability) report of an experiment, the SUMMARY tab provides a concise overview of interpretability findings, highlighting key features and evaluating the model's overall performance. The content in the SUMMARY tab may vary depending on the experiment type (regular or time-series) and the interpretability methods used. Typically, it presents the most important variables (features) of the H2O Driverless AI model, ranked by importance in descending order, and indicates whether these features are original or transformed. Additionally, in the SUMMARY tab, when the MLI report originates from an H2O Driverless AI model, it includes a table summarizing the H2O Driverless AI model.

  1. Click the SUMMARY tab.
note

To learn more about the Summary tab, see Summary tab.

Validation score​

For the default credit card model, in the SUMMARY tab, the H2O Driverless AI model received a validation (Area Under the ROC Curve) score of 0.78513. When a binary classification model, such as the default credit card model, receives an AUC score of 0.78513 in the MLI report from an H2O Driverless AI model, it indicates the model's performance in distinguishing between the two classes. AUC measures the model's ability to correctly rank the instances of positive and negative classes, with a higher score indicating better discrimination. In this case, a score of 0.78513 suggests that the model is reasonably effective at distinguishing between default and non-default instances, although the interpretation of the exact level of performance may vary depending on the specific context and requirements of the task.

H2O Driverless AI table with a focus on the validation AUC

Top 5 most important variables (features)​

For the default credit card model, in the SUMMARY tab, the top 5 most important variables (features) for the default credit card model, all originating from the original features (variables), are as follows:

  • PAY_1: Payment status in September (Original)
  • PAY_2: Payment status in August (Original)
  • PAY_AMT1: Amount of previous payment in September (Original)
  • PAY_5: Payment status in May (Original)
  • PAY_3: Payment status in July (Original)

Summary tab of an MLI report

Now that you have explored the summary tab, Task 6 will guide you in diving deeper into the DAI model tab.

Feedback