MLA-C01 Question 434
Single answerYou are building a machine learning pipeline on AWS to predict customer churn. The dataset is stored in Amazon S3, and you need to preprocess the data and train a model. The preprocessing involves filling in missing values, normalizing numeric features, and encoding categorical variables. Which AWS service should you use to build and orchestrate this pipeline efficiently, considering minimal manual intervention and scalability?
- A
Amazon SageMaker Pipelines
- B
AWS Glue
- C
Amazon EMR
- D
Amazon Comprehend
Show answer and explanation
Correct answer: A
Explanation
Amazon SageMaker Pipelines is the most appropriate service for orchestrating machine learning workflows, including data preprocessing, model training, and deployment. It is designed to integrate seamlessly with other AWS machine learning services and minimizes manual intervention while ensuring scalability. Other options, like AWS Glue and Amazon EMR, are more suitable for general data processing tasks, and Amazon Comprehend focuses on NLP-specific tasks.
- A. Correct.
Amazon SageMaker Pipelines is purpose-built for machine learning workflows and enables efficient orchestration of preprocessing, training, and deployment tasks. It is ideal for this use case.
- B. Incorrect.
AWS Glue is a data integration service designed for ETL (extract, transform, load) tasks, but it is not specifically optimized for machine learning workflows or model training.
- C. Incorrect.
Amazon EMR is a big data processing service that can handle distributed data processing tasks, but it requires more manual setup to integrate with machine learning pipelines.
- D. Incorrect.
Amazon Comprehend is a natural language processing service and is not relevant for building machine learning pipelines or preprocessing tabular datasets.