A healthcare company is deploying an ML model to aws video

Full Certification Question

A healthcare company is deploying an ML model to predict patient readmission rates using Amazon SageMaker. The company’s ML engineer is setting up a CI/CD pipeline using AWS CodePipeline to automate the model retraining and deployment process. The pipeline must automatically trigger when new training data is uploaded to an Amazon S3 bucket. The goal is to retrain the model and deploy it for real-time inference. Given this context, consider the following steps: The pipeline deploys the model version in SageMaker Model Monitor for real-time inferences. A new data upload triggers the pipeline via an Amazon S3 event notification. The pipeline deploys the retrained model to a SageMaker endpoint for real-time predictions. Amazon SageMaker retrains the model using updated data stored in the S3 bucket. An S3 Lifecycle rule attempts to start the pipeline when fresh data arrives. Which three steps should be selected and ordered correctly to configure the pipeline?