Financial institutions process thousands of documents daily, including tax forms, loan statements, and purchase orders. Each has a unique format, structure, and field names, making it challenging to create automation workflows using optical character recognition (OCR) software. Amazon Bedrock Data Automation (BDA) helps solve these challenges by automating the extraction, validation, and analysis of data from financial documents. BDA goes beyond simple OCR by using foundation models that can:

While foundation models like Anthropic Claude can extract content from PDFs, Amazon Bedrock Data Automation offers custom extractions with industry-leading accuracy at a lower cost, along with features such as visual grounding with confidence scores for explainability and built-in hallucination mitigation.

In this post, we explore how Amazon Bedrock Data Automation can accurately extract information from four common types of financial documents: bank statements, W-2 forms, 1099-B tax forms, and vendor contracts. We highlight the complexity in the documents, detail the custom extraction created in Amazon Bedrock Data Automation, and describe the outcomes of the extraction process.

Amazon Bedrock Data Automation lets you configure output based on your processing needs using blueprints. A blueprint in Amazon Bedrock Data Automation is a configuration template that defines how data should be extracted from documents. It specifies:

Think of it as a map that tells Amazon Bedrock Data Automation exactly what information to look for and how to process it. When using a blueprint for extraction, you can use a catalog blueprint or a custom created blueprint. A custom blueprint allows organizations to create extraction patterns for their specific needs. In this post, we created custom blueprints and used the BDA console to generate and validate the output.

The following sections walk you through creating custom blueprints for bank statements, W-2 forms, 1099-B forms, and vendor contracts.