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…

SageMaker Canvas is a no-code solution suitable for business analysts, but it might offer less control over specific data cleaning steps compared to Data Wrangler, and its "automatic" model preparation might not be as transparent or flexible as using a dedicated algorithm like XGBoost for a data scientist.

SageMaker Data Wrangler provides a visual interface to easily perform data cleaning tasks like handling empty fields, duplicate values, and rare values, reducing manual coding effort. SageMaker XGBoost is a highly efficient and widely used algorithm for tabular binary classification problems like churn prediction, offering strong performance with relatively straightforward implementation for data scientists.

This choice is incomplete and therefore invalid. If it implied using Canvas for cleaning and a built-in algorithm, Canvas itself provides auto-ML, making a separate "built-in" algorithm redundant in that context.

While SageMaker Data Wrangler for cleaning combined with SageMaker Autopilot for auto-ML training offers low effort, the prompt might prefer the more explicit control over the algorithm (XGBoost) for this specific type of prediction, and Data Wrangler+XGBoost is a common, efficient pattern for data scientists.