Google Professional Machine Learning Engineer exam dumps

Google Professional Machine Learning Engineer practice question 234 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 234

Select 2Google Cloud Platform

You are tasked with designing a real-time analytics pipeline for a machine learning model that processes streaming data from IoT sensors. The data needs to be preprocessed, stored for historical analysis, and queried for insights. Which combination of Google Cloud services would best meet the requirements for scalable data storage, real-time querying, and cost-effectiveness?

  1. A

    Cloud Storage for data storage, BigQuery for querying, and Dataflow for real-time preprocessing

  2. B

    Bigtable for data storage, BigQuery for querying, and Pub/Sub for real-time preprocessing

  3. C

    Cloud Storage for data storage, Cloud Spanner for querying, and Dataflow for real-time preprocessing

  4. D

    BigQuery for data storage, Looker for querying, and Pub/Sub for real-time preprocessing

  5. E

    Cloud Storage for data storage, BigQuery for querying, and Pub/Sub for real-time preprocessing

Show answer and explanation

Correct answers: A, E

Explanation

The combination of Cloud Storage, BigQuery, and Dataflow or Pub/Sub provides a scalable, cost-effective solution for processing and analyzing streaming IoT data. Cloud Storage can handle large volumes of raw data cost-effectively, BigQuery supports fast and flexible querying, and Dataflow or Pub/Sub can manage real-time ingestion and preprocessing tasks. These services work together seamlessly to create an end-to-end analytics pipeline.

  • A. Correct.

    Correct: Cloud Storage is cost-effective for storing large datasets, BigQuery is optimized for querying structured data, and Dataflow is ideal for real-time data preprocessing.

  • B. Incorrect.

    Incorrect: Bigtable is suitable for low-latency, high-throughput, key-value workloads, but it is not optimized for querying like BigQuery. Pub/Sub is useful for messaging but not for preprocessing.

  • C. Incorrect.

    Incorrect: Cloud Spanner is a globally distributed database designed for transactional workloads, not for querying large-scale analytical data.

  • D. Incorrect.

    Incorrect: BigQuery is more suitable for scalable data storage and querying, while Looker is a BI tool for visualization and analysis. Pub/Sub does not handle preprocessing.

  • E. Correct.

    Correct: Cloud Storage is optimal for storing raw data, BigQuery is ideal for querying preprocessed data, and Pub/Sub enables real-time ingestion and preprocessing.

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. 235.Your team is building a machine learning pipeline to analyze customer transaction data stored in a...
  2. 236.You are building a machine learning pipeline to train and evaluate a model for predicting product...
  3. 237.You are building a machine learning pipeline to process a large dataset stored in Google Cloud...
  4. 238.You are designing a machine learning pipeline for a recommendation system, and you need to store a...
  5. 239.You are designing a machine learning pipeline on Google Cloud to process data from multiple...
Back to the Google Professional Machine Learning Engineer exam dumps