Google Professional Machine Learning Engineer
Get started today
Ultimate access to all questions.
You are working on a project where you need to build classification workflows for several structured datasets stored in BigQuery. The classification will need to be performed multiple times, and you want to avoid writing any code for tasks such as exploratory data analysis, feature selection, model building, training, hyperparameter tuning, and serving. Given these non-coding requirements, what should you do?
You are working on a project where you need to build classification workflows for several structured datasets stored in BigQuery. The classification will need to be performed multiple times, and you want to avoid writing any code for tasks such as exploratory data analysis, feature selection, model building, training, hyperparameter tuning, and serving. Given these non-coding requirements, what should you do?
Explanation:
The correct answer is B: Train a classification Vertex AutoML model. This option is ideal because Vertex AutoML provides a codeless end-to-end machine learning solution that covers all the necessary steps, including exploratory data analysis, feature selection, model building, training, hyperparameter tuning, and serving. Options A and D require coding, and option C, while relevant for classification, also requires some coding. Therefore, Vertex AutoML is the best option for avoiding code altogether.