Google Cloud Professional Machine Learning Engineer — Question 321

You are creating a retraining policy for a customer churn prediction model deployed in Vertex AI. New training data is added weekly. You want to implement a model retraining process that minimizes cost and effort. What should you do?

Answer options

• A. Retrain the model when a significant shift in the distribution of customer attributes is detected in the production data compared to the training data.
• B. Retrain the model when the model's latency increases by 10% due to increased traffic.
• C. Retrain the model when the model accuracy drops by 10% on the new training dataset.
• D. Retrain the model every week when new training data is available.

Correct answer: A

Explanation

The correct answer is A because it focuses on retraining the model based on significant changes in data distribution, which is crucial for maintaining model performance without unnecessary retraining. Options B and C are reactive measures that do not ensure timely updates based on data changes, while option D could lead to excessive costs and effort without ensuring that the model is truly required to be retrained.