AWS Certified Machine Learning – Specialty — Question 274

A digital media company wants to build a customer churn prediction model by using tabular data. The model should clearly indicate whether a customer will stop using the company's services. The company wants to clean the data because the data contains some empty fields, duplicate values, and rare values.

Which solution will meet these requirements with the LEAST development effort?

Answer options

• A. Use SageMaker Canvas to automatically clean the data and to prepare a categorical model.
• B. Use SageMaker Data Wrangler to clean the data. Use the built-in SageMaker XGBoost algorithm to train a classification model.
• C. Use SageMaker Canvas automatic data cleaning and preparation tools. Use the built-in SageMaker XGBoost algorithm to train a regression model.
• D. Use SageMaker Data Wrangler to clean the data. Use the SageMaker Autopilot to train a regression model

Correct answer: A

Explanation

SageMaker Canvas is a no-code tool that allows users to automatically clean tabular data and train machine learning models, making it the option with the least development effort. Customer churn prediction (will/will not stop using services) is a binary classification task, which requires a categorical model rather than a regression model. Other options involving SageMaker Data Wrangler and manual training with XGBoost require significantly more development and configuration effort.