Google Cloud Professional Machine Learning Engineer — Question 280

You work for a hospital. You received approval to collect the necessary patient data, and you trained a Vertex AI tabular AutoML model that calculates patients' risk score for hospital admission. You deployed the model. However, you're concerned that patient demographics might change over time and alter the feature interactions and impact prediction accuracy. You want to be alerted if feature interactions change, and you want to understand the importance of the features for the predictions. You want your alerting approach to minimize cost. What should you do?

Answer options

• A. Create a feature drift monitoring job. Set the sampling rate to 1 and the monitoring frequency to weekly.
• B. Create a feature drift monitoring job. Set the sampling rate to 0.1 and the monitoring frequency to weekly.
• C. Create a feature attribution drift monitoring job. Set the sampling rate to 1 and the monitoring frequency to weekly.
• D. Create a feature attribution drift monitoring job. Set the sampling rate to 0.1 and the monitoring frequency to weekly.

Correct answer: D

Explanation

The correct answer is D because creating a feature attribution drift monitoring job allows you to track changes in feature importance over time, which is crucial for understanding prediction accuracy as demographics shift. By setting the sampling rate to 0.1, you can minimize costs while still gaining valuable insights. Options A and B focus on feature drift without assessing the importance of features, and option C uses a higher sampling rate, which may lead to unnecessary costs.