ReleaseBytes
aws AWS What's New ·

AWS Glue Data Quality adds anomaly detection and Catalog integration

dataawsengineer
feature

AWS Glue Data Quality now supports anomaly detection for data quality evaluations, using ML-powered forecasting to identify unexpected changes without manual threshold rules. It also allows writing evaluation results, including anomaly predictions, back to AWS Glue Data Catalog tables for queryable records. These features benefit data engineers monitoring many tables and offer a consistent experience across ETL jobs and Catalog evaluations, available in all commercial and GovCloud regions.

  • →Anomaly detection for data quality evaluations
  • →Write data quality results to AWS Glue Data Catalog
  • →Consistent experience across workflows
  • →Availability
Features (2) ›
  • Anomaly detection for data quality evaluations

    AWS Glue Data Quality now supports anomaly detection for Catalog-based evaluations, utilizing ML-powered time-series forecasting to identify unexpected changes in data statistics without requiring explicit threshold rules.

  • Write data quality results to AWS Glue Data Catalog

    Evaluation results, including rule outcomes, profiling metrics, and anomaly predictions with confidence bounds, are now written back to AWS Glue Data Catalog tables, creating a queryable record of all quality evaluations.

Notes (2) ›
  • Consistent experience across workflows

    These new capabilities function consistently for both ETL jobs and direct Catalog evaluations, providing data engineers with a unified data quality experience regardless of their workflow type.

  • Availability

    AWS Glue Data Quality anomaly detection and Catalog results storage are available in all AWS commercial regions and AWS GovCloud (US) regions.

Read the original announcement →

https://aws.amazon.com/about-aws/whats-new/2026/07/aws-glue-data-quality-catalog-anomaly-detection-write-results

Related releases