In this era where smartphone and tablet usage permeates nearly all of life, it only seems logical that the purchase of a home would eventually move in the digital direction as well. This certainly creates a situation where the loan package can be digitally moved with minimal cost rather than printed (multiple times, most likely) and physically moved between geographies. Therefore, processing delays associated with in-transit time and cost can be reduced, improving the overall process for both lender and borrower.
However, while borrowers may be able to upload copies of their paystubs and bank statements for example, the data must still be gleaned from those documents as part of the underwriting process. Without the aid of sophisticated OCR, that gleaning process remains a manual process, even though the mortgage is “digital”.
With the costs to process each mortgage continuing to rise, lenders must leverage automation to improve profitability and consistency in their business processes. With advanced mortgage OCR solutions, mortgage companies will reduce their level of manual document indexing and data entry activity, enabling them to process more loans per day at a lower cost per loan – yielding a leaner process and increased profit margins.
Paradatec’s Advanced Mortgage OCR solution does more than just convert document images to text. Once converted, that text is then processed by our artificial intelligence (“AI”) rules engine in the same way a human being would process the content. Based on these rules, documents are automatically indexed and relevant data points are extracted. This information is then passed to downstream applications for appropriate routing, decisioning, and archival.
Our process begins with a full-page OCR scan of each image, typically completed in less than one second per page. This high-speed performance allows every word on the page to be included in the scope of the AI rules engine analysis, just as a human being would interpret the content. This content evaluation process is unique to Paradatec in terms of the combination of speed and ability to include all page content in the evaluation scope, thereby making it extremely flexible with documents of varying layout (for example, bank statements).
Other OCR solutions typically expect relevant data points to consistently appear in the same locations (or ‘zones’) on a document. If the data shifts due to changes in layout (again, think of bank statements), the zone-based approach will fail unless another layout template is created, making for a greater administrative burden with these solutions.
A high volume, scalable OCR automation initiative requires the flexibility of Paradatec’s Advanced Mortgage OCR solution to process an unlimited number of document layouts without needing to develop specific templates for each layout variation. This capability is unique to Paradatec and a vital feature for creating an effective unstructured document classification and data capture solution.
Applying the right technology in the digital lending world can drive down cost providing lenders with a significant competitive advantage.
About The Author
Mark Tinkham is Director of Business Alliances at Paradatec, Inc. Over the past twenty-five plus years, Mark has worked for technology companies that deliver innovative solutions to the financial services industry. For the past ten years, his primary focus has been bringing efficiencies to the mortgage market through industry leading Optical Character Recognition (OCR).