Google Professional Machine Learning Engineer
Get started today
Ultimate access to all questions.
You work for a magazine distributor and need to build a machine learning model that predicts which customers will renew their subscriptions for the upcoming year. Using your company’s historical subscription and customer data as your training set, you created a TensorFlow model and deployed it to Vertex AI. You are now required to determine which customer attribute (e.g., age, gender, last purchase date) has the most predictive power for each prediction served by the model. What approach should you take to achieve this?
You work for a magazine distributor and need to build a machine learning model that predicts which customers will renew their subscriptions for the upcoming year. Using your company’s historical subscription and customer data as your training set, you created a TensorFlow model and deployed it to Vertex AI. You are now required to determine which customer attribute (e.g., age, gender, last purchase date) has the most predictive power for each prediction served by the model. What approach should you take to achieve this?
Explanation:
The correct answer is B: Use Vertex Explainable AI. Submit each prediction request with the explain keyword to retrieve feature attributions using the sampled Shapley method. This approach allows you to understand the importance of each feature for individual predictions by using the Shapley method, which is a well-known technique for providing feature attributions. This method is integrated into Vertex AI, making it a straightforward and powerful choice for determining which customer attribute has the most predictive power for each prediction served by the model.