Google Cloud Professional Machine Learning Engineer — Question 197

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?

Answer options

• A. Create a BigQuery table. Use BigQuery ML to build a boosted tree classifier. Inspect the partition rules of the trees to understand how each prediction flows through the trees.
• B. Create a Vertex AI tabular dataset. Train an AutoML model to predict customer purchases. Deploy the model to a Vertex AI endpoint and enable feature attributions. Use the “explain” method to get feature attribution values for each individual prediction.
• C. Create a BigQuery table. Use BigQuery ML to build a logistic regression classification model. Use the values of the coefficients of the model to interpret the feature importance, with higher values corresponding to more importance
• D. Create a Vertex AI tabular dataset. Train an AutoML model to predict customer purchases. Deploy the model to a Vertex AI endpoint. At each prediction, enable L1 regularization to detect non-informative features.

Correct answer: B

Explanation

The correct answer is B, as it involves using Vertex AI's feature attribution capabilities to explain individual predictions, which is crucial for understanding how different factors influence customer purchasing behavior. Option A focuses on boosted trees, which may not provide the same level of interpretability. Option C, while useful for understanding feature importance, does not offer the same individual prediction insights as feature attributions. Option D is incorrect because enabling L1 regularization is not directly related to interpreting individual predictions.