Q58 — AWS SAA-C03 Ch.10

Question 58 of 100 | ← Chapter 10

Q658. A company that uses AWS needs a solution to predict the resources needed for manufacturing processes each month.The solution must use historical values that are currently stored in an Amazon S3 bucket. The company has no machine learning (ML) experience and wants to use a managed service for the training and predictions.Which combination of steps will meet these requirements?(Select TWO.)

Correct Answer: B. Use Amazon SageMaker to train a model by using the historical data in the S3 bucket, E. Train an Amazon Forecast predictor by using the historical data in the S3 bucket

Explanation

To meet the requirements of predicting resources needed for manufacturing processes using historical values stored in an Amazon S3 bucket, the following combination of steps will be appropriate:B. Use Amazon SageMaker to train a model by using the historical data in the S3 bucket.E. Train an Amazon Forecast predictor by using the historical data in the S3 bucket.Here's the rationale behind these steps:Step 1: Use Amazon SageMaker to train a modelAmazon SageMaker is a managed service that provides capabilities for building, training, and deploying machine learning models. By utilizing SageMaker, you can train a model using the historical data stored in the Amazon S3 bucket. This step involves configuring SageMaker with appropriate settings and initiating the training process.Step 2: Train an Amazon Forecast predictorAmazon Forecast is a fully managed service specifically designed for time-series forecasting. With this service, you can train models to predict future values based on historical data. In this case, you would train an Amazon Forecast predictor using the historical data stored in the S3 bucket. This would involve setting up the necessary configurations and initiating the training process in Amazon Forecast.The other options do not align with the requirements or involve unnecessary steps:Option A suggests deploying an Amazon SageMaker model and creating a SageMaker endpoint for inference. While deploying a model and creating an endpoint is necessary for making predictions, it does not address the training aspect using the historical data.Option C suggests configuring an AWS Lambda function with a function URL that uses Amazon SageMaker endpoints to create predictions based on inputs. While deploying a Lambda function to utilize SageMaker endpoints is a valid approach for making predictions, it does not cover the training aspect using historical data.Option D suggests configuring an AWS Lambda function with a function URL that uses an Amazon Forecast predictor to create a prediction based on inputs. While using Lambda and Amazon Forecast for predictions is suitable, it does not involve training the predictor with historical data from the S3 bucket.Therefore, the combination of steps B and E is the most appropriate for meeting the stated requirements.