A data engineer builds a pipeline that feeds customer data to an Azure Machine Learning model for churn prediction. The security team needs to ensure that training data containing personal information is identified and tracked for data lineage purposes. Which Microsoft Purview feature should be used?
Select an answer to reveal the explanation.
Short Explanation
Here's the deal — you need Microsoft Purview Data Map with automated scanning and classification because it scans data sources, identifies sensitive information types, and tracks lineage from source to Azure Machine Learning datasets. That gives you visibility into personal data in AI training pipelines.
Full Explanation
Microsoft Purview Data Map with automated scanning and classification is correct because it provides automated data scanning and classification that identifies sensitive information types in data sources, and it tracks data lineage showing how data flows from source to Azure Machine Learning datasets, enabling visibility into personal data in AI training pipelines. Microsoft Purview Information Barriers to segment training data is incorrect because Information Barriers control communication and collaboration between groups, not data tracking in ML pipelines. Microsoft Purview eDiscovery with custodian tracking is incorrect because eDiscovery is for legal hold and content search in compliance scenarios, not ongoing data lineage tracking. Microsoft Purview Compliance Manager with data inventory assessment is incorrect because Compliance Manager provides regulatory compliance assessments but does not scan and classify data in ML training pipelines.