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?