Google Professional Machine Learning Engineer exam dumps

Google Professional Machine Learning Engineer practice question 407 of 522

Professional Machine Learning Engineer. Professional level, Google Cloud. Free question with the correct answer and a full explanation.

Google Professional Machine Learning Engineer Question 407

Select 2Google Cloud Platform

You are tasked with designing an end-to-end machine learning pipeline for a fraud detection model on Google Cloud using TFX. The pipeline must ingest data from BigQuery, transform the data for training, and deploy the model to Vertex AI for serving. Which combination of TFX components would you use to build the pipeline?

  1. A

    BigQueryExampleGen, Transform, Trainer, Pusher

  2. B

    CsvExampleGen, Transform, Trainer, Evaluator

  3. C

    BigQueryExampleGen, Transform, Trainer, Evaluator, Pusher

  4. D

    DataflowExampleGen, Transform, Trainer, Pusher

  5. E

    BigQueryExampleGen, StatisticsGen, Transform, Trainer, Pusher

Show answer and explanation

Correct answers: A, C

Explanation

To design an end-to-end pipeline with TFX for the given scenario, you need components that align with each step: BigQueryExampleGen for data ingestion from BigQuery, Transform for feature engineering, Trainer for model training, and Pusher for deployment to Vertex AI. Optionally, Evaluator may be included for model evaluation. Options 1 and 3 correctly cover these requirements, while the others either include incorrect components or miss critical steps.

  • A. Correct.

    Correct. BigQueryExampleGen is used to ingest data directly from BigQuery, Transform is used for feature engineering, Trainer for model training, and Pusher to deploy the model to Vertex AI.

  • B. Incorrect.

    Incorrect. CsvExampleGen is used for CSV file ingestion, which is not suitable since the data source is BigQuery. Additionally, it does not include Pusher for deployment.

  • C. Correct.

    Correct. This option includes BigQueryExampleGen for data ingestion, Transform for data preprocessing, Trainer for model training, Evaluator for model evaluation, and Pusher for deployment to Vertex AI.

  • D. Incorrect.

    Incorrect. DataflowExampleGen is not a TFX component. Data ingestion from BigQuery is handled by BigQueryExampleGen.

  • E. Incorrect.

    Incorrect. While BigQueryExampleGen, StatisticsGen, Transform, Trainer, and Pusher are valid TFX components, StatisticsGen is not explicitly needed for the pipeline described in the scenario.

Timed practice exam

Take a Google Professional Machine Learning Engineer practice test under exam conditions

60 questions in 120 minutes, drawn from this bank, with a score report and a per-question review when you finish.

Start timed exam

More Google Professional Machine Learning Engineer practice questions

  1. 408.You are designing a machine learning pipeline using TensorFlow Extended (TFX) components on Google...
  2. 409.You are tasked with automating the retraining of a machine learning model deployed on Google Cloud....
  3. 410.You are managing a machine learning model deployed on Google Cloud, which predicts customer churn...
  4. 411.You are managing a machine learning model in production on Google Cloud. The model performance has...
  5. 412.You are designing a machine learning pipeline on Google Cloud to predict product demand. The...
Back to the Google Professional Machine Learning Engineer exam dumps