DevOps Articles

Classifying and Extracting Mortgage Loan Data with Amazon Textract

https://aws.amazon.com/polly/ Mortgage loan applications, at least in the United States, comprise around 500 or more pages of diverse documents. In order for applications to be reviewed, all these documents need to be classified, and the data on each form extracted.

Today, a new Analyze Lending API, for analyzing and classifying the documents contained in mortgage loan application packages, and extracting the data they contain, is available for https://aws.amazon.com/textract/.

When a mortgage application package is uploaded, the workflow classifies the documents in the package before routing them to the right ML model, based on their classification, for data extraction.

To do this in the demo console, I click the Upload package button and provide a single file, up to 5 MB, and 10 pages maximum for testing in the demo console, containing documents to analyze.