A hospital runs a nightly batch inference job with an ML model that validates x-ray results. The hospital needs to produce a daily report on model data quality and model performance. Which solution will provide the required daily monitoring and reporting?

Amazon SageMaker Model Monitor is specifically designed for continuous monitoring of ML models in production, including batch inference jobs. It automatically detects data drift, model quality degradation, and other issues by comparing incoming inference data against a baseline. Scheduling a monitoring job in Model Monitor will generate the necessary daily reports on model data quality and performance. Creating a CloudWatch dashboard with resource metrics would monitor the infrastructure running the batch job, not the model's data quality or performance. AWS Glue DataBrew is for data preparation and quality assessment before model training, not for monitoring a deployed model's inference data. A SageMaker AI pipeline with a QualityCheck step is for monitoring during the pipeline execution (e.g., training or processing), not for continuous monitoring of a deployed model's inference endpoint or batch job results.