Question

A data science team has finished training and evaluating a fraud-detection model. They now need to make the model available so that a payment application can send transaction data and receive real-time predictions with low latency. Which Amazon SageMaker capability is designed for this part of the ML development lifecycle?

Accepted Answer

SageMaker real-time inference endpoints to host the model and serve predictions on demand

Answer

SageMaker Data Wrangler to prepare and transform the raw transaction data

Answer

SageMaker Ground Truth to label the historical transaction records

Answer

SageMaker Experiments to compare different training runs and hyperparameters