nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #206

You work for a retail company. You have been asked to develop a model to predict whether a customer will purchase a product on a given day. Your team has processed the company's sales data, and…

The correct answer is B. Create a Vertex AI tabular dataset. Train an AutoML model to predict customer purchases. To interpret individual predictions of a customer purchase model, use Vertex AI AutoML with a tabular dataset to leverage its built-in Explainable AI capabilities.

Submitted by helene.fr· Apr 18, 2026ML model development

Question

You work for a retail company. You have been asked to develop a model to predict whether a customer will purchase a product on a given day. Your team has processed the company's sales data, and created a table with the following rows: - Customer_id - Product_id - Date - Days_since_last_purchase (measured in days) - Average_purchase_frequency (measured in 1/days) - Purchase (binary class, if customer purchased product on the Date) You need to interpret your model's results for each individual prediction. What should you do?

Options

  • ACreate a BigQuery table. Use BigQuery ML to build a boosted tree classifier. Inspect the partition
  • BCreate a Vertex AI tabular dataset. Train an AutoML model to predict customer purchases.
  • CCreate a BigQuery table. Use BigQuery ML to build a logistic regression classification model. Use
  • DCreate a Vertex AI tabular dataset. Train an AutoML model to predict customer purchases.

How the community answered

(49 responses)
  • A
    4% (2)
  • B
    78% (38)
  • C
    12% (6)
  • D
    6% (3)

Why each option

To interpret individual predictions of a customer purchase model, use Vertex AI AutoML with a tabular dataset to leverage its built-in Explainable AI capabilities.

ACreate a BigQuery table. Use BigQuery ML to build a boosted tree classifier. Inspect the partition

While boosted tree models can provide some feature importance, 'inspect the partition' does not directly provide a clear interpretation for each individual prediction in the same granular way as feature attributions.

BCreate a Vertex AI tabular dataset. Train an AutoML model to predict customer purchases.Correct

Training an AutoML model on a Vertex AI tabular dataset provides built-in Explainable AI (XAI) features, including instance-level feature attributions, which allow you to understand how each specific feature contributed to an individual customer's purchase prediction. This directly addresses the need to interpret the model's results for each individual prediction.

CCreate a BigQuery table. Use BigQuery ML to build a logistic regression classification model. Use

While BigQuery ML with SHAP can provide individual prediction explanations, Vertex AI AutoML offers integrated and often more user-friendly Explainable AI features directly within the platform for tabular models, making it a more streamlined approach.

DCreate a Vertex AI tabular dataset. Train an AutoML model to predict customer purchases.

Visualizing global feature importance helps understand the overall model's behavior but does not provide an explanation for the specific outcome of each individual prediction.

Concept tested: Vertex AI AutoML Tabular Explainable AI

Source: https://cloud.google.com/vertex-ai/docs/tabular/understand-model-predictions

Topics

#Model Explainability#Vertex AI AutoML#Tabular Data#Prediction Interpretability

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice