MLS-C01 · Question #362
A bank has collected customer data for 10 years in CSV format. The bank stores the data in an on-premises server. A data science team wants to use Amazon SageMaker to build and train a machine learnin
The correct answer is B. Upload the data into an Amazon S3 bucket. Allow SageMaker to access the data that is in the. To prepare 10 years of on-premises CSV data for churn prediction using Amazon SageMaker with the least development effort, the solution involves uploading data to Amazon S3, using SageMaker Data Wrangler for transformations and insights, then exporting the prepared data to S3 for
Question
A bank has collected customer data for 10 years in CSV format. The bank stores the data in an on-premises server. A data science team wants to use Amazon SageMaker to build and train a machine learning (ML) model to predict churn probability. The team will use the historical data. The data scientists want to perform data transformations quickly and to generate data insights before the team builds a model for production. Which solution will meet these requirements with the LEAST development effort?
Options
- AUpload the data into the SageMaker Data Wrangler console directly. Perform data transformations
- BUpload the data into an Amazon S3 bucket. Allow SageMaker to access the data that is in the
- CUpload the data into the SageMaker Data Wrangler console directly. Allow SageMaker and
- DUpload the data into an Amazon S3 bucket. Allow SageMaker to access the data that is in the
How the community answered
(49 responses)- A14% (7)
- B73% (36)
- C8% (4)
- D4% (2)
Why each option
To prepare 10 years of on-premises CSV data for churn prediction using Amazon SageMaker with the least development effort, the solution involves uploading data to Amazon S3, using SageMaker Data Wrangler for transformations and insights, then exporting the prepared data to S3 for training.
Directly uploading 10 years of customer data in CSV format into the SageMaker Data Wrangler console is not the intended or scalable method for large datasets; Data Wrangler primarily connects to existing data sources like S3.
Uploading the large CSV dataset to Amazon S3 provides scalable and durable storage, which is the standard input for SageMaker services. Amazon SageMaker Data Wrangler is specifically designed to reduce development effort for data preparation, feature engineering, and generating data insights quickly from S3 data sources, before feeding the transformed data back to S3 for subsequent SageMaker model training.
Similar to option A, directly uploading large datasets to the Data Wrangler console is not the primary or most efficient ingestion method, and Data Wrangler's strength lies in connecting to existing data sources.
While Amazon S3 is the correct storage, SageMaker Feature Store is designed for operationalizing and sharing curated features, not for the initial exploratory data transformations and insights needed before model building, which is best handled by SageMaker Data Wrangler.
Concept tested: Data preparation and feature engineering with SageMaker Data Wrangler
Source: https://aws.amazon.com/sagemaker/data-wrangler/
Topics
Community Discussion
No community discussion yet for this question.