Exam AWS Certified Solutions Architect - Associate SAA-C03 topic 1 question 687 discussion

"Amazon Forecast is no longer available to new customers. Existing customers of Amazon Forecast can continue to use the service as normal" "After careful consideration, we have made the decision to close new customer access to Amazon Forecast, effective July 29, 2024." This question will either be removed or reformulated to exclude Forecast as the service is no longer available to new customers.

Because of these assertions - The company has no machine learning (ML) experience - The comapny wants to use a managed service We could tempted to go for SageMaker that is the core AWS managed service for ML purposes . But, but, if we consider this valuable information: - A company that uses AWS needs a solution to predict the resources needed for manufacturing processes. With a bit research, we will find out that AWS also hold time-series forecasting service based on machine learning (ML). https://aws.amazon.com/forecast/?nc1=h_ls So i understand options DE are the best answers enven thought this service is not mentionned anywhere in current SAA-C03 course version

Status update - reading on the latest changes to Sagemaker, there is an option as well for no-code solution, so your guess is as good as mine on this question.

Because the company has no ML experience, the following... An Amazon Forecast predictor is a trained machine learning model that uses time series data to generate forecasts. It leverages various algorithms to learn from your data and produce accurate predictions for future values. Sagemaker - need ML experience, Forecaster, no ML experience

D and E Why: Amazon Forecast is a fully managed time-series forecasting service that requires no ML expertise. E. Train an Amazon Forecast predictor with the historical data in S3. D. Invoke that predictor (e.g., behind a Lambda with a function URL or API Gateway) to generate monthly predictions. Why not SageMaker (A/B/C): SageMaker is powerful but assumes more ML familiarity and management overhead than Forecast, which is purpose-built for this use case.

D. Configure an AWS Lambda function with a function URL that uses an Amazon Forecast predictor to create a prediction based on the inputs. Amazon Forecast is a managed service specifically designed for time series forecasting and can be used without extensive ML knowledge. This option allows for easy integration with Lambda for making predictions. E. Train an Amazon Forecast predictor by using the historical data in the S3 bucket. This option is essential for creating the forecasting model using the historical data stored in S3. Amazon Forecast is designed to handle this type of task and is user-friendly for those without ML experience.

Amazon Forecast is no longer available to new customers as of July 29, 2024. However, for the AWS Certified Solutions Architect – Associate (SAA-C03) exam, Amazon Forecast may still appear as a valid service since the exam content often lags behind recent announcements. Since the company has no ML expertise, A B C are all out, because they require prior SageMaker knowledge. That would make the answers: D & E. But IRL (in real life, not a web service), you must consider SageMaker Canvas, because it "includes the key capabilities found in Forecast, including the ability to train an ensemble of forecasting models using both statistical and neural network algorithms. It creates the best model for your dataset by generating base models for each algorithm, evaluating their performance, and then combining the top-performing models into an ensemble".

so what about AB since the Forcase is no logner available to new customers?

Amazon Forecast is no longer available to new customers. https://aws.amazon.com/blogs/machine-learning/transition-your-amazon-forecast-usage-to-amazon-sagemaker-canvas/

Amazon forecast can be trained by using data from S3: https://docs.aws.amazon.com/forecast/latest/dg/getting-started.html

BE from CHATGPT

SageMaker and Forecast can directly utilize data within an S3 B) E) https://aws.amazon.com/blogs/compute/build-workflows-for-amazon-forecast-with-aws-step-functions/ https://docs.aws.amazon.com/sagemaker/latest/dg/train-model.html

A + B dude

Yes, exactly. Steps B and A together constitute a comprehensive solution: - Step B involves using Amazon SageMaker to train a machine learning model using historical data stored in the S3 bucket. - Step A involves deploying the trained model as a SageMaker endpoint, allowing for real-time inference on new data. This combination leverages Amazon SageMaker's managed services for both training and inference, meeting the company's requirements efficiently.

A & B: B. Amazon SageMaker is a managed service that provides built-in algorithms and tools for training machine learning models. You can use SageMaker to train a model using historical data stored in an S3 bucket. This meets the requirement of utilizing a managed service for training the model without requiring machine learning experience. A. Once the model is trained using SageMaker, you can deploy it by creating a SageMaker endpoint for inference. This endpoint allows you to make predictions based on new data, fulfilling the requirement of predicting resources needed for manufacturing processes each month.

*E*: Amazon Forecast is a fully managed service that uses machine learning (ML) to generate highly accurate forecasts without requiring any prior ML experience. Forecast is applicable in a wide variety of use cases, including estimating product demand, energy demand, workforce planning, computing cloud infrastructure usage, traffic demand, supply chain optimization, and financial planning. *D*: Publish demand using AWS Lambda, AWS Step Functions, and Amazon CloudWatch Events rule to periodically (hourly) query the database and write the past X-months (count from the current timestamp) demand data into the source Amazon S3. https://aws.amazon.com/blogs/machine-learning/automating-your-amazon-forecast-workflow-with-lambda-step-functions-and-cloudwatch-events-rule/

B & D is the right choice