Answer-first summary for fast verification
Answer: 1. Specify sampled Shapley as the explanation method with a path count of 5. 2. Deploy the model to Vertex AI Endpoints. 3. Create a Model Monitoring job that uses prediction drift as the monitoring objective.
The correct answer is A. Sampled Shapley is a fast and scalable approximation of the Shapley value, which is suitable for online prediction requests because it can return feature attributions with minimal latency. A lower path count (like 5) ensures lower latency in explanations. Creating a Model Monitoring job that uses prediction drift as the monitoring objective is appropriate because it can detect changes in model predictions that might indicate a change in feature attributions over time.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
No comments yet.
You have trained an XGBoost model that you plan to deploy on Vertex AI for online prediction. Vertex AI is a robust platform for ML model deployment and management. You are in the process of uploading your model to the Vertex AI Model Registry. You need to configure an explanation method to ensure that online prediction requests return with minimal latency. Additionally, you want to be alerted if there are any meaningful changes in feature attributions over time. What should you do?
A
B
C
D