Professional Cloud Architect · Free Practice Question Medium
Question 9
You are a cloud architect and have been assigned a task to develop a model that will predict the type of product a customer is most likely to purchase next, based on their past purchases and behavior. The client has a massive amount of historic data available but lacks machine learning expertise. Furthermore, the solution needs to be able to constantly learn from new data. Which of the following would be the best approach for this situation?
-
A
Use BigQuery ML, retrain the model manually with new data.
-
B
Use AutoML Vision, retrain the model periodically with new data.
-
C
Use Cloud Machine Learning Engine with TensorFlow and retrain the model manually with new data.
-
D
Use AutoML Tables, retrain the model periodically with new data.
Reveal correct answer
Correct answer: D
A.
BigQuery ML allows machine learning models to be built using SQL queries, but in this case, it might not be suitable as it requires manual retraining and might not be as flexible or automated as AutoML for complex predictive models.
B.
AutoML Vision is incorrect because it is designed for image analysis tasks, not for analyzing structured tabular data.
C.
Cloud Machine Learning Engine with TensorFlow might be a viable solution for some scenarios, but in this case, it requires manual model training and deep machine learning expertise, which is not available according to the scenario.
D.
AutoML Tables is the right solution because it is specifically designed for tabular or structured data, like historic purchase data. AutoML allows for automatic model training, tuning, and deployment, which suits the lack of machine learning expertise. It also allows the model to be retrained periodically with new data, which meets the requirement of constantly learning from new data.
Discussion
Think the marked answer is wrong, or have a better explanation? Share it below — comments appear after review.
