We are excited to announce the launch of prediction explanations for Amazon Fraud Detector machine learning (ML) models, available via both the AWS Console and SDK. Prediction explanations report the impact of the predictors (or input variables) on a fraud score, which helps customers achieve greater visibility into how an ML model arrived at a particular fraud score. Amazon Fraud Detector (AFD) is a fully managed service that makes it easy to identify potentially fraudulent online activities, such as the creation of fake accounts or online payment fraud. Using ML under the hood and based on over 20 years of fraud detection expertise from AFD automatically identifies potentially fraudulent activity in milliseconds—with no ML expertise required.

AWS IoT Greengrass is now available in Canada (Central) region. AWS IoT Greengrass is an Internet of Things (IoT) edge runtime and cloud service that helps customers build, deploy, and manage device software. With AWS IoT Greengrass, customers can have their connected devices run AWS Lambda functions, Docker containers, or both, execute predictions based on machine learning models, keep device data in sync, and communicate with other devices securely – even when not connected to the Internet.

Amazon QuickSight now supports comparative (e.g., year-over-year) and cumulative (e.g., year-to-date) time period functions. These new functions allow QuickSight authors to quickly implement advanced date/time calculations without having to use complicated row offsets or pre-computed columns, allowing these calculations to be added in regular business reporting, trend analysis and time series analysis. For further details, visit here .

You can now create Apache Airflow 2.2 environments on Amazon Managed Workflows for Apache Airflow (MWAA). Apache Airflow 2.2 is the latest version of the popular open-source tool that helps customers author, schedule, and monitor workflows. Further, MWAA will install Python requirements, provider packages, and plugins on the Airflow web server starting with 2.2 environments.

AWS Resilience Hub, which provides a central place to define, validate, and track the resilience of your applications on AWS, has just launched in 13 additional AWS Regions: US West (N. California), Africa (Cape Town), Asia Pacific (Hong Kong), Asia Pacific (Mumbai), Asia Pacific (Seoul), Asia Pacific (Sydney), Canada (Central), Europe (London), Europe (Milan), Europe (Paris), Europe (Stockholm), Middle East (Bahrain), and South America (São Paulo).

Amazon RDS Performance Insights now supports collection and tracking of query execution plans for Amazon RDS for Oracle, so you can more easily identify if a change in the query execution plan is the cause of a worse performing or a stuck query.

You can now access five new metrics when using AWS PrivateLink for VPC Endpoints and VPC Endpoint Services. AWS PrivateLink is a fully-managed private connectivity service that enables customers to access AWS services, third-party services or internal enterprise services hosted on AWS in a secure and scalable manner while keeping network traffic private. 

Customers in the AWS Asia Pacific (Jakarta) Region can now use Amazon Elastic File System (Amazon EFS).

Amazon Relational Database Service (Amazon RDS) for PostgreSQL and Amazon RDS on AWS Outposts now support PostgreSQL major version 14. PostgreSQL 14 includes performance improvements for parallel queries, heavily-concurrent workloads, partitioned tables, logical replication, and vacuuming. PostgreSQL 14 also improves functionality with new capabilities. For example, you can cancel long-running queries if a client disconnects and you can close idle sessions if they time out. In addition, stored procedures now return data.

Amazon EC2 G4dn instances which provide a cost-effective GPU platform for deploying machine learning models in production and graphics-intensive applications are now available in the Asia Pacific (Osaka) AWS region.