Bottom Line: Huntington Bank reduced data redaction of over 400 million documents from years to months by using AWS services like Textract and Step Functions for automated, scalable processing with over 95% accuracy.
The Huntington National Bank developed an automated solution to search and redact over 400 million documents for sensitive customer data. Where traditional procedures would have taken years, the process was completed in months through the use of Amazon Textract and AWS Step Functions.
Huntington is one of the ten largest banks in the United States and has managed hundreds of millions of documents in an on-premises system since 2015. In 2025, the institution launched a proactive compliance initiative to systematically search its archives for sensitive customer data such as Social Security numbers, account numbers, and personal addresses, and redact them. The documents exist in various file formats.
The requirements for the solution were strictly defined: encryption in transit and at rest, access controls on storage locations, compliance with PCI-DSS standards, resynchronization to on-premises systems, and a redaction accuracy of at least 95%. Huntington relied on AWS DataSync for secure data migration over AWS Direct Connect, Amazon S3 for storage, AWS Key Management Service for encryption, and Amazon Textract for automated text recognition from scanned documents. Orchestration was handled by AWS Step Functions and Lambda functions.
The central challenge lay in scaling: to process millions of documents daily, Huntington had to optimize Amazon Textract’s throughput limits. This required increasing service quotas through the AWS Service Quotas Console and careful control of request rates to avoid throttling. The solution combined asynchronous Textract jobs with Step Functions orchestration to achieve optimal parallelization while adhering to service guidelines.
For CTOs in financial institutions, the approach demonstrates how cloud-native services can be deployed for legacy data stores without incurring significant organizational risks: The solution adhered to strict compliance requirements, used secure data transfer, and ensured that no data remains in AWS – all data is replicated back to on-premises systems. Reducing project duration from years to months enables institutions to implement compliance requirements promptly rather than defer them.
Source: aws.amazon.com · Published June 24, 2026
Lumi AI News — AI-assisted curation pursuant to Art. 50 EU AI Act. Paraphrase and classification by Lumi News Pipeline v1.7.1.