Friday, February 16, 2007

Capsilon: decoding the PDF document

In the early days, going paperless meant launching a scanning department and grabbing an image of every document in the process and then storing them electronically. Some lenders got famous doing this and it truly did offer some compelling advantages. One thing it didn't offer was the ability to easily extract data from those images for use in other technology tools.

The first pioneers in this area were the technology firms that support title companies. Back when I was editing Real Estate Technology Insight, I was covering a number of firms that were working to pull the data out of imaged public record documents in order to speed up title searches.

Today, we find that San Diego-based Capsilon is offering a data extraction technology that can pull data points from the pages of a PDF document. This is important because for all the benefits of the Fannie Mae SMART Doc, many lenders and investors will continue to produce electronic loan documents in PDF format.

This new, automated data extraction works independently, or in tandem with Loan Katalyst, the company’s recently released Intelligent Document Management system, which automatically classifies loan file documents as they enter the origination system. Katalyst’s online collaborative portal allows many permitted users to view and take action on loan files simultaneously, with full security.

Capsilon says that this tool will reduce errors and make underwriting, quality control and due diligence audits less labor intensive. The company says that appraisal reports will be one area lenders will be using its technology as a number of appraisal programs produce reports as PDF files.

No comments: