You work for a retail company that is using a regression model built with BigQuery ML to predict product sales. This model is currently being used to serve online predictions to optimize inventory and sales strategies. Recently, you developed a new version of the model that uses a different architecture (custom model). Initial analysis revealed that both models are performing as expected in terms of prediction accuracy and latency. You now want to deploy the new version of the model to production and monitor its performance over the next two months. Your main objective is to minimize the impact on existing users and ensure a smooth transition. How should you deploy the model? | Google Professional Machine Learning Engineer Quiz