The new capabilities enable users to generate statistical data profiles to monitor dataset shape and completeness, both on catalog tables at rest and on streaming data in Visual ETL workflows. Anomaly detection identifies deviations without requiring preset thresholds, adapting over time as data patterns evolve.
Profiles and anomalies are tracked historically via a dedicated Studio tab, facilitating ongoing data quality management. This feature supports proactive identification of data drift critical for reliable machine learning model performance and data governance.
Source & further reading
Amazon SageMaker Unified Studio now supports data profiling and anomaly detection ↗Source published 2026-08-18. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.