Blend reports that it has integrated a new breed of OCR software “natively” in its mortgage point-of sale platform in order to eliminate the need for the manual “stare-and-compare” process that loan teams have employed for eons.
The firm says its new Blend Vision is a form of computer visioning that can parse uploaded lender-required documentation to determine if certain conditions are met, then trigger automated follow-ups to satisfy those conditions. As such, it can greatly speed the automated mortgage pre-approval process.
The software extracts the data from uploaded documentation at the point-of-sale. It then uses a decisioning engine to determine if the proper documents were uploaded and if the proper requirements have been met.
Blend says this will provide lenders with efficiency gains that ultimately translate to higher margins, quicker closing times, and lower origination costs.
Despite the advent of the all-digital mortgage, most mortgage lenders today still use manual stare-and-compare techniques in order to compare the information in uploaded paper documents with other data such as electronic bank statements, the firm points out in a release.
The goal with Blend Vision is to extract borrower data from paper documents uploaded at the point of sale, then immediately run it through a decisioning engine and intelligently trigger workflows based off it.
The company says this is the first step along a much longer journey to get the most out of data trapped in uploaded documents.