Google Cloud Professional Machine Learning Engineer — Question 194

You work for a retail company. You have created a Vertex AI forecast model that produces monthly item sales predictions. You want to quickly create a report that will help to explain how the model calculates the predictions. You have one month of recent actual sales data that was not included in the training dataset. How should you generate data for your report?

Answer options

• A. Create a batch prediction job by using the actual sales data. Compare the predictions to the actuals in the report.
• B. Create a batch prediction job by using the actual sales data, and configure the job settings to generate feature attributions. Compare the results in the report.
• C. Generate counterfactual examples by using the actual sales data. Create a batch prediction job using the actual sales data and the counterfactual examples. Compare the results in the report.
• D. Train another model by using the same training dataset as the original, and exclude some columns. Using the actual sales data create one batch prediction job by using the new model and another one with the original model. Compare the two sets of predictions in the report.

Correct answer: B

Explanation

Option B is correct because generating feature attributions allows you to see the impact of each feature on the predictions, which is crucial for understanding the model's reasoning. Option A simply compares predictions without insights into their calculation, while option C involves counterfactuals that may complicate the analysis. Option D unnecessarily trains another model instead of leveraging the existing one, which is less efficient for understanding the current model's predictions.