Amazon SageMaker Autopilot, which makes it easy to create highly accurate machine learning models, now provides a model explainability report generated by Amazon SageMaker Clarify, making it easier to understand and explain how the models you create with SageMaker Autopilot make predictions. Explainability reports include feature importance values so you can understand how each attribute in your training data contributes to the predicted result as a percentage. The higher the percentage, the more strongly that feature impacts your model’s predictions. You can download the explainability report as a human readable file, view model properties including feature importance in Amazon SageMaker Studio, or access feature importance using the SageMaker Autopilot APIs .

Amazon EMR now supports Amazon EC2 Instance Metadata Service (IMDS) v2, in addition to v1, for all IMDS calls to EMR clusters. Instance metadata is data about your instance that you can use to configure or manage the running instance. IMDSv1 is fully secure and AWS will continue to support it. But IMDSv2 adds new “belt and suspenders” protections for four types of vulnerabilities that could be used to try to access the IMDS. For more information, please read the
AWS Security blogpost .

AWS Data Exchange now enables providers to copy descriptions, data sets, and public offers from their existing products to a new product. With this launch, providers can select any existing product, published or unpublished, and copy all of its details to a new draft product, which they can then modify as needed and publish within a few seconds. For providers that frequently create new products that share similar metadata, this will save a significant amount of time and effort.

We are pleased to announce the launch of Building Data Lakes on AWS. Data lakes enable organizations to generate business value by identifying and acting upon opportunities for business growth. This new one-day classroom course will help you practice building a data lake in a hands-on environment.  An expert instructor will teach you how to build and secure a data lake using AWS Lake Formation while also showing you how to optimize for cost and performance.

On March 30 2021, Amazon Pinpoint announced the launch of new Journey controls to allow customers to customize their user experience, and when messages are sent. Journeys are multi-step campaigns that can be executed across SMS, email, and push messages. Journeys are intended for customers with user engagement use cases, and who need to be precise on when messages are delivered to their users.

AWS Step Functions is now integrated with Amazon EMR on Amazon Elastic Kubernetes Service (Amazon EKS), making it easier to integrate Apache Spark based jobs into your analytics pipeline. You can now build workflows including steps to manage EMR on EKS virtual clusters and submit jobs without writing code to manage the state of the job.

Pipeline Factory is an AWS Solutions Consulting Offer delivered via a consulting engagement from Mphasis Stelligent, an AWS DevOps Competency Partner. Pipeline Factory enables DevOps teams to define, build, and publish standardized pipelines that enforce quality, security, and governance throughout the software delivery lifecycle. Customers that request this consulting offer will participate in an engagement that delivers discovery and design, Pipeline Factory implementation, and publication and deployment of standardized Pipeline Products.

Amazon CloudWatch Container Insights for Amazon Elastic Container Service (Amazon ECS) is now available in the AWS Africa (Cape Town) region. Using Container Insights, DevOps and systems engineers can monitor, isolate, and diagnose containerized applications and microservices environments through automated dashboards. This helps you visualize the performance and health of Amazon ECS and AWS Fargate resources including clusters, tasks, containers, and services.  

AWS Global Accelerator now supports traffic through the new AWS edge location in Jakarta, Indonesia. Using Global Accelerator, users in Indonesia can now see improved performance of up to 20% for internet traffic to the AWS Singapore Region and up to 60% for traffic to AWS Regions in North America and Europe. Global Accelerator is now available through 96 Points of Presence globally and supports application endpoints in more than 20 AWS Regions.  

Amazon DocumentDB (with MongoDB compatibility) is a fast, scalable, highly available, and fully managed document database service that supports MongoDB workloads. As a document database, Amazon DocumentDB makes it easy to store, query, and index JSON data at scale.