Google Professional Machine Learning Engineer
Get started today
Ultimate access to all questions.
Comments
Loading comments...
Ultimate access to all questions.
Your company's Customer Care and Support Office has been using an NLP model to assess general customer satisfaction across its main service categories, with satisfactory performance. Due to a recent expansion in services, you are tasked with refining and updating the model to include new product categories, as well as automating the model's retraining and evaluation processes on Google Cloud Platform (GCP). The solution must consider cost efficiency, scalability, and the dynamic nature of customer feedback data. Which of the following strategies would you implement to achieve these goals? (Choose two correct options)
A
Develop a new model exclusively with data from the newly added services and use an ensemble method to combine predictions from both the old and new models.
B
Retrain the existing model using only the most recent week's customer feedback data to quickly adapt to changes in customer satisfaction trends.
C
Update the existing model by incorporating feedback data from the new services and establish a scheduled retraining and evaluation pipeline to ensure the model remains accurate over time.
D
Defer any updates to the model, assuming its current accuracy and generalization capability will suffice for the new services without additional retraining.
E
Implement a continuous integration/continuous deployment (CI/CD) pipeline for the model that automatically retrains and deploys the model based on new data, while also setting up monitoring for model performance and data drift.