Posts

Make Sure That Your OCR Tech Works

Paradatec, Inc., a provider of advanced Optical Character Recognition (OCR) solutions for mortgage file processing, announced the availability of their One-Day Blind Test Challenge. Paradatec’s OCR library identifies nearly 500 unique document types in the typical mortgage file, along with extracting over 6,000 data fields from those documents. Combining this library with Paradatec’s sub-second OCR processing engine creates a high level of performance and scalability. Through this new One-Day Blind Test Challenge, qualified organizations can see the power of Paradatec’s out-of-the-box OCR solution for themselves, providing a final buying decision validation point using samples of their own mortgage files.

Featured Sponsors:

 

 
“Many of our prospects have been disappointed in the results of past OCR initiatives, so they’re understandably cautious. Our One-Day Blind Test Challenge lets them run samples of their loans through our solution to validate our out-of-the-box performance claims. The Challenge will be conducted on-site rather than at our facilities, due in part to the confidential nature of the content, but to also minimize concerns about our skewing any results behind the scenes,” said Neil Fraser, Paradatec’s Director of US Operations.

Featured Sponsors:

 
Fraser continues, “Our mortgage OCR library offers clients a short implementation timeline while other solutions require development from the ground up. This One-Day Blind Test Challenge demonstrates the validity of our claim so prospects can be assured that Paradatec offers a robust and scalable solution ready to deliver productivity improvements in weeks rather than months or years.”

Featured Sponsors:

 
In the course of the Blind Test Challenge, the provided loan files will be indexed by document type; 100 data fields will be extracted from various key documents like the Note, Deed of Trust, Closing Disclosure, Appraisal, and W-2; and a bookmarked PDF of the loan will be produced, with the data extraction fields highlighted using Paradatec’s new WritePDF module. Fraser concludes his statements by saying, “Unfortunately, many companies base their buying decision primarily on price, only to be disappointed with the lack of true out-of-the-box mortgage-specific functionality offered by the product. In other cases, great claims are made regarding OCR automation rates, while the typical experience found with other products is something less impressive. We believe ours is the most expansive OCR offering available, such that we’ll gladly test it on a blind set of loans to show a prospect what makes Paradatec different.”

Progress In Lending
The Place For Thought Leaders And Visionaries

The Future Of Digital Mortgage Technology Innovation

High-powered mortgage executives gathered at the Seventh Annual ENGAGE Event in Denver, Colo., to discuss the future of the mortgage business. The discussions that happened were both lively and informative. Here’s how they see the future of digital mortgage technology innovation:

Featured Sponsors:

 

 
“We have to move this industry forward by streamlining the process, and cutting the cost to originate,” said Michael Hammond, Chief Strategy Officer at PROGRESS in Lending Association and the Founder and President of NexLevel Advisors. NexLevel provides solutions in business development, strategic selling, marketing, public relations and social media. “This is far more then just hype. This is something that the industry has to do and it is not just about one technology or one platform, it is about coming together as an industry.”

Neil Fraser, Director of U.S. Operations at Paradatec, believes that this will be an evolutionary process. “You don’t need a revolution to convert the document into data that you can believe. You need technology to read the documents, and convert that to data that can be both read and understood. I see that as an evolutionary step in mortgage technology innovation.”

Featured Sponsors:

 
Paradatec is a mortgage OCR technology organization that automates the data entry operations of large lenders through intelligent document analysis. Neil was Paradatec’s first U.S. employee and has grown the organization every year since the company incorporated here in 2002.

As the mortgage industry embraces innovation to become more digital, everything starts at the point-of-sale. Realizing this fact, a lot of new POS vendors have emerged claiming to offer the true digital mortgage experience. Curt Tegeler, President of WebMax, warns lenders not to be fooled by vaporware as they march toward more digital processes.

Featured Sponsors:

 
“There’s a lot of buzz today around the digital POS. Why is that? We’ve found that 90% of homebuyers start the process online,” Tegeler notes. WebMax’s digital lending platforms expedites the borrowing process, helps maintain compliance, delivers dynamic online lending tools, and provides a highly innovative borrower experience. “Make sure that the executives behind your POS have deep mortgage experience. You have to understand the market so you know what you’re fixing.”

One area that everyone agrees needs fixing is the appraisal process. If the industry is going to move to a more data-driven process and a fully automated point-of-sale, slower processes like the appraisal need to be addressed.

“Appraisals were really left on the side,” noted Arturo Garcia, the Senior Vice President of Account Management at Mercury Network. He leads all customer retention efforts and strategies for the company, responsible for continuous improvements and increased returns for customer investments and overall satisfaction. “Appraisals didn’t get a lot of attention. However, it’s antiquated to send an appraiser out to the field time and time again. I envision a day when you have a system that can automatically flag issues with the appraisal, fix them or send them right back to the appraiser for fixing.”

The big takeaway from this discussion was that the digital lending process is coming and must touch all parts of the mortgage process in order to make a difference in how loans are done.

About The Author

 

Tony Garritano
Tony Garritano is chairman and founder at PROGRESS in Lending Association. As a speaker Tony has worked hard to inform executives about how technology should be a tool used to further business objectives. For over 10 years he has worked as a journalist, researcher and speaker in the mortgage technology space. Starting this association was the next step for someone like Tony, who has dedicated his career to providing mortgage executives with the information needed to make informed technology decisions. He can be reached via e-mail at tony@progressinlending.com.

Tackling Industry Change

We are gradually morphing to a more next-generation mortgage process and some say it’s about time. Lenders are notoriously slow to embrace change. So, why are things different this time? There are so many new outside factors that are forcing lenders to evolve. To discuss how change is impacting the mortgage industry we gathered a panel of experts that includes: (left to right) Neil Fraser, Director of US Operations at Paradatec, a mortgage OCR technology; Brandon Perry, President at TTP Enterprises, a leading CRM firm; Michael L. Riddle, the Managing Director at Mortgage Resources Group, LLC.; and Paul Wetzel, EVP, Product at Mortgage Cadence. Here’s how they see the future of mortgage lending:

Featured Sponsors:

 

Q: How have recent mortgage technology vendor M&As changed the mortgage industry?

NEIL FRASER: It is common, and often a natural progression in many industries that they start out fragmented and consolidate as they mature. The purported advantages to consolidation can include: economies of scale, more resources for research and development, and better marketing and market reach.

Paradatec monitors the M&A activity of companies that we know well. The reality of consolidation, in many cases is very different from expectations. Just like in other verticals.

Featured Sponsors:

The consolidations we see appear to be aimed at allowing the larger mortgage technology providers to become one-stop shops for all things tech and to move that technology further down the food chain to smaller banks and credit unions.

But M&A is a risky approach. Some recent consolidations have led to organizational confusion, and a general loss of focus.

Ultimately they find that the organizations’ cultures have little in common, and the perceived synergies between the two companies are illusive. In fact, in some cases we have seen this mistake repeated multiple times over several short years. Generally, a great deal of marketing hype follows such consolidations. So, the goal of increased marketing reach is often realized, but is only short term. However, the reality is that the loss of focus can be devastating to both their clients and employees.

We believe these risks are common in the case where unique and significant differentiators make a particular technology company’s products and services clearly superior. For a technology vendor in this position, there are many potential disadvantages to consolidation. In the recent past we believe we have been witnessing the negative results of some of these mergers, especially in our niche of advanced OCR technology for the mortgage industry.

Featured Sponsors:

Paradatec has historically made its living by licensing our sophisticated mortgage OCR solutions to some of the largest banks and lenders in the country through OEM relationships with larger partners. Our solutions traditionally were only used in very large lenders. The net effect of the consolidation of the last few years is that our current and future re-sellers are able to leverage very sophisticated OCR technology to smaller organizations that never could support such platforms themselves.

PAUL WETZEL: Leading vendors are looking to add to their product offerings and/or customer base with acquisitions. Where the reason for the acquisition is augmenting the product offering, this can frequently be a faster time to market versus building the functionality natively. Having said this, acquisitions are not always guaranteed to be successful. Considerations like cultural fit of new teams vs. the acquirer, and compatibility of technology stacks are two key considerations among many others.

MICHAEL L. RIDDLE: I think it depends on whom you talk to and which specific companies that you are referring to. In some instances, larger technology providers have acquired smaller providers for a specific technology, market niche or just to gain market share. Traditionally, these types of M&A don’t always work out because there isn’t synergy between the technology platforms, corporate cultures don’t mesh, and customer bases don’t align.

However, when the right companies merge, ones that have a shared vision for the future, corporate cultures that align, technology platforms that easily integrate, and where the sum is greater than its individual parts, there can be significant advantages for industry participants. This type of merger or acquisition has the power to disrupt an industry.

Speaking from experience, the second example is what has transpired with our new merger. MRG has formed a partnership with Asurity Technologies (Asurity) that brings together Treliant Solutions, LLC, Risk Management Solutions, Inc. (RMS) and Mortgage Resources Group, LLC (MRG) into an integrated best-in-class compliance platform.

In addition to delivering legally defensible compliance expertise, in-depth compliance insights with state-of-the-art technology to document mortgage transactions, we can now also provide HMDA, CRA, Fair Lending, and Redlining solutions. This provides our clients with a significantly more comprehensive compliance solution.

BRANDON PERRY: The mortgage technology vendor space seems to be mirroring the mortgage industry in regards to M&A activity. With the mortgage lender M&A activity, the competitive landscape with technology vendors is extremely high. Smaller boutique vendors are strategically acquired by larger well-funded looking to expand or enhance their product offerings.
The current trend is for the larger vendors to serve as one-stop shops for mortgage lenders. This is good news for the mortgage industry as it nicely sets the table for further innovation by start ups or boutique technology vendors looking to plug the holes left by the larger players.

Q: How has new regulation changed the mortgage industry?

NEIL FRASER: Regulation equates to reporting in order to attain measurement and control. As regulation has increased in this market, the need for originators and services to quickly extract meaningful content from their loan files to support such regulatory demands has increased as well.

The Paradatec solution can assist with data gathering for many regulatory events, but one that’s especially burdensome in terms of executive liability is the Fed’s Comprehensive Capital Analysis and Review (CCAR). The CCAR is an assessment of the capital adequacy of thirty-four large U.S. bank holding companies and was introduced as part of the Dodd-Frank Act. The effects of the Dodd-Frank Act in general are widespread and relatively well known. CCAR is focused on, evaluating capital adequacy even under stressful conditions. Reporting for CCAR came through the FR Y-14M forms in June 2012 which support a dictionary of around 250 data fields to be collected and presented to the Fed.

One of the early effects of CCAR 14-M reporting has been that large lenders have taken extra responsibility for the accuracy of data presented to the Fed for their loans. That includes loans originated via the correspondent channel or acquired otherwise. For Paradatec, as a specialist in automatically reading mortgage documents via Optical Character Recognition (OCR), this presented an opportunity to provide automated audit of LOS data vs actual scanned images of original paperwork in order for entities to comply.

For 2017 CFOs of CCAR entities are obliged to attest that, not only is their CCAR 14-M data is “materially correct to the best of their knowledge” but also to “the effectiveness of internal controls and include those practices necessary to provide reasonable assurance as to the accuracy of these data”. In other words “I’ve checked all my data”. This is a big task especially for banks that acquire loans they did not originate. CCAR entities are effectively now required to check all their loan paperwork vs LOS data and attest that they match. That’s a huge undertaking without sophisticated OCR technology.

MICHAEL L. RIDDLE: The regulatory environment for today’s mortgage lender has become exceedingly complex. Compliance becomes more difficult each day, as a cascade of new disclosure and lending requirements are imposed by federal, state and local regulators.

With this avalanche of regulation, it is becoming very difficult for mortgage lenders to gauge whether their internal compliance systems are functioning properly and whether the continuing cost, in both human and financial terms, of adopting and maintaining adequate regulatory controls, can be sustained in a volatile origination market.

Lenders, in order to cope with these added regulatory compliance risks, are faced with an immediate and compelling need to re-evaluate and upgrade the capacity of their internal systems to recognize and incorporate mandated regulatory changes. Static document systems and templates simply will not suffice to keep you compliant. To en- sure compliance, mortgage disclosure and documents systems need to be dynamically constructed.

At the same time, the absolute risk of non-compliance has become intolerable. Audits by regulators and investors alike are now commonplace and fines, penalties, and loan repurchase demands are escalating. As tough new regulatory standards increase the scope and absolute number of loans that must be evaluated carefully for compliance, investors have become acutely aware that several regulatory changes impose liability on the purchase of a mortgage loan for compliance errors made by its originator. It is no surprise that investors are increasingly demanding, prior to funding a loan purchase, that originators provide loan specific data in an electronic format complete enough to permit comprehensive automated compliance reviews on each loan to be purchased.

PAUL WETZEL: New regulations and GSE requirements have pushed technology providers to look for creative ways to address both the ongoing release of requirements themselves but also what kind of technology upgrades might be necessary to better accommodate the strong likelihood that this level of change will continue for years to come. While new regulations must always be accommodated as a priority, customers will not tolerate regulation support being the focal point of a technology vendor’s roadmap. Leading vendors always need to be upgrading their technology platforms and better accommodating the ongoing drumbeat of regulation is one key driver for this. The pressure of regulation is also a key driver for ongoing consolidation of mortgage technology vendors as some vendors will look to exit the market by selling their business vs. investing to upgrade their technology per the above.

BRANDON PERRY: With the heightened awareness of compliance with new regulation in the mortgage industry, many lenders have paused delivery and implementation of solutions, which drive new business. I’ve mentioned “compliance doesn’t matter” quite often in the past couple of years and it still holds true today. While compliance can’t be ignored, lenders must not fall into the trap of hypersensitivity to rules and regulations and then completely ignore the basic need to grow your business. The most successful lenders have been able to find a nice balance between regulation and business growth.

Q: How has talk of and interest in the digital mortgage changed the mortgage industry?

NEIL FRASER: 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 that direction as well. This certainly creates a situation where the loan package can be moved electronically at no cost, rather than printed (multiple times, most likely) and physically moved between geographies. Therefore, in-transit time and cost can be reduced, which is great for the market.

At the same time, we don’t believe the digital mortgage negates the need for certain underlying technologies, including OCR. While a borrower may be able to upload PDF copies of their paystubs and bank statements, as an example, the data must still be gleaned from those documents as part of the underwriting process. Without the aid of sophisticated OCR such as that provided by Paradatec, that gleaning process remains a manual process, even though the mortgage is “digital”.

Organizations looking to embrace the ‘digital mortgage’ concept should look to not only eliminate the paper that exists in their process today, but also lean-out their business processes with the aid of technology so the per-loan processing costs can be reduced.

BRANDON PERRY: I believe much of the interest and talk of digital mortgage rose from the ashes of the constantly fluctuation regulatory environment. With the birth of compliance as a new cost center in most lenders, the pressure to absorb these new expenses must be released. I previously mentioned the importance of new business growth, but pressure can be released internally by finding ways to more efficiently process loans. Mortgage executives challenging their current processes helped pave the way to embrace technology allowing for digital mortgage.
One of the biggest challenges with digital mortgage is information security. With the ever-growing list of data breaches, cyber security will never be more important to the mortgage industry as we enter the digital mortgage world. The nature of the extremely sensitive information held by mortgage lenders makes them prime targets for cyber attacks.

PAUL WETZEL: Core concepts related to digital mortgages of course are not new but there is certainly growing interest in these topics over the past couple years and that is a very good thing for the mortgage industry. Fintech has been an underinvested segment and lenders’ interest in spending to improve digital outcomes is driving investment into mortgage technology. When executed correctly by a vendor, digital mortgage becomes a menu of options open to each lender that improve borrower experience, speed time to close and staff efficiency, and increase the transparency and security of the transaction. This will help both the lenders top line and bottom line as well as improving their standing in the industry.

MICHAEL L. RIDDLE: The first thing that comes to mind is the user experience. All the talk of the digital mortgage has changed borrower expectations. Since that now famous Super Bowl Ad that launched Rocket Mortgage and borrowers expectations, consumers demand technology that delivers a quick and simple user experience that matches the type of every day experience that they have on the Internet with the likes of Google, Apple and Amazon.

This has forced the industry to focus attention on delivering a dynamic and mobile digital experience. Many companies have invested heavily in technology and on being able to provide the types of tools consumers are look for on the front end. But what lenders must realize is the fact that to truly deliver on the digital experience the entire mortgage process needs to be streamlined not just the point of sale.

This includes compliantly documenting each and every financial transaction digitally. To be able to maintain a competitive edge in the digital age requires an understanding of data-security, technical capability, industry experience, compliance insights, legal expertise, matched with seamlessly integrated systems and robust data interfaces to actually streamline the lending process while delivering on the digital mortgage experience.

Q: Lastly, how do you see the mortgage industry and the mortgage process of the future evolving as a result of these and other big changes?

PAUL WETZEL: It’s an exciting time to be in the mortgage industry with respect to how technology can be used to dramatically improve outcomes. Lenders should be pressing their mortgage technology vendor partners for their view and strategies related to the above. Healthy vendors who plan to not just survive but thrive need to be active in the M&A space, have new a creative ways to accommodate ongoing regulation, and established but growing digital mortgage capabilities. Seismic shifts like the end of paper won’t happen overnight for the industry but they won’t happen at all leading lenders being willing to be front runners and we’re starting to see more lenders being willing to be just that.

MICHAEL L. RIDDLE: As mentioned earlier, the regulatory environment has become exceedingly complex, and I don’t see that changing anytime soon. That will continue to put pressure on lenders to comply, which will highlight the need for an advance compliance ecosystem— One that is comprehensive, can track, monitor and provide real time insights for all of a lenders compliance needs.

In addition, borrower expectations will continue to push the envelope on delivering the digital mortgage experience that today’s borrower demands. That requires the right balance of advanced technology, deep mortgage expertise, legal insights, industry integrations, with the ability to constantly evolve.

BRANDON PERRY: We’ve become a culture accustomed to instant gratification with nearly everything in our daily routine. Rather than heading to the store, how about same day delivery? We’re upset when a website has a two second delay loading. I’ve heard countless radio commercials from car dealers touting how fast they get you in and out when buying a car.   We are kidding ourselves if we believe obtaining a mortgage is the only exception. The next big competitive environment is time. I believe the time to pre-approval, approval and closing in the next few years will be fractional to the current process timeline of today.

NEIL FRASER: This industry is experiencing an evolution through the aid of technology like many others before. While the regulatory requirements will certainly control what the experience looks like for the consumer, automation within the process will continue to expand…the increasing per-loan processing costs dictate as much. Industry leaders such as Amazon and Orbitz have made the self-service model albeit in other segments, much less daunting, and the speed at which transactions can be completed has decreased significantly through this evolution. While the magnitude of the buying decision for a home is obviously much greater than that of buying an airplane ticket or a box of diapers, the consumer has become comfortable with online transactions to the point that a paper-bound process is viewed as slow and stodgy.

The process will continue to evolve, both due to competitive pressures as well as consumer-driven expectations. But, like a lot of the other ‘digital transformations’ that have occurred, we believe the mortgage market will be “both…and” situation, as in both paper and digital, rather than an exclusively digital model, at least for the foreseeable future. Until the entire consumer community is ready to embrace a digital-only approach, paper will continue to be a part of the process, and therefore vendors that automate paper reading will continue to add value.

Progress In Lending
The Place For Thought Leaders And Visionaries

Vendor Releases Innovative Web Services API

Paradatec, Inc., developer of an Optical Character Recognition (OCR) solution for mortgage file processing, has released their web services API for real-time integration to their clients’ line-of-business applications. This new functionality can seamlessly transfer documents from the loan origination system (LOS) to the Paradatec solution for page classification and data extraction, with the Paradatec-produced results transferred back to the LOS in place of manual data entry.

Featured Sponsors:

 

 
“As application integration becomes tighter in response to the ongoing compression of service level timeframes, Paradatec’s new web services API stands ready to serve as the OCR extension to our clients’ line-of-business applications. Our first solution to leverage this capability is our new WriteUCD module, in which the final Closing Disclosure (CD) is submitted to us through the web services API, our OCR functionality extracts the relevant data from the CD, and WriteUCD then produces the corresponding Uniform Closing Dataset (UCD) file required by Fannie Mae and Freddie Mac” said Neil Fraser, Paradatec, Inc.’s Director of US Operations.

Featured Sponsors:

 
“This new functionality allows for seamless OCR processing scaling from small document sets like borrower-provided paystubs and W-2s up to full loan files. With the ability to integrate tightly with any other web service-enabled application, we’re helping our clients create a very rich and efficient application ecosystem.”

Featured Sponsors:

 
Paradatec’s OCR solutions offer significant efficiencies for classifying large quantities of differing document types and extracting key data elements from those documents.  In the mortgage market, these capabilities allow for the quick and accurate identification of over 500 unique documents in the typical mortgage file, along with capturing nearly any data element from those documents that an organization requires.

About The Author

Tony Garritano
Tony Garritano is chairman and founder at PROGRESS in Lending Association. As a speaker Tony has worked hard to inform executives about how technology should be a tool used to further business objectives. For over 10 years he has worked as a journalist, researcher and speaker in the mortgage technology space. Starting this association was the next step for someone like Tony, who has dedicated his career to providing mortgage executives with the information needed to make informed technology decisions. He can be reached via e-mail at tony@progressinlending.com.

OCR For Mortgage In Action

The financial services industry is challenged with managing large volumes of documents with varying layouts containing immense amounts of data – part of which is highly critical with regards to compliance. The traditional manual process for classifying and keying data from these documents is time consuming, error prone, and costly due to the sheer volume and complexity of the mortgage documents. In an industry where standardizing forms is not always possible due to their varying systems and points of origination, an acceptable automation solution must be able to properly and compliantly handle this variability.

Client:

Top-Five Originator. This bank is one of the largest in the United States. It is a leading lender offering a range of quality home loans, including government and conventional. These loans are provided through multiple channels.

Featured Sponsors:

 

 
Challenge

The mortgage lending industry presents a number of unique challenges for classifying and extracting data from key documents. This is due in part to the large volumes of disparate document variations found in most loan files.

>>A typical incoming mortgage loan file may contain 250 to 600+ pages of various size documents, comprising more than 250 potential document types. Older loans files may grow to well over 1000 pages.

Featured Sponsors:

 
>>Manually sorting each set of loan documents is a labor intensive and error prone effort, typically requiring the addition of document separator pages if the file is to be scanned.

>>Due to the sheer labor effort required, the typical level of detailed document sorting possible with a manual approach is very “coarse”. In other words, only the most critical documents and document groups are classified rather than attempting to identify all specific document types. An example of this limitation might be a manual grouping of a series of specific documents into a “Credit Documents Group” rather than breaking these out specifically by document types such as bank statements, credit reports, and brokerage statements.

>>To compete in this extremely competitive market segment, organizations are looking for ways to reduce costs and streamline their processes.

In addition to the challenges described above, this top five originator was looking for a solution to help automate the laborious task of providing data for a number of audit-centric applications. These ad-hoc projects commonly had tight timelines and included wide ranges of loans, and millions of pages to be audited.

Featured Sponsors:

 
Project Description

At the start of the Project, this top five originator had a sophisticated document capture infrastructure feeding a well-known enterprise content management system in place. What was missing from this infrastructure was an advanced recognition module that could deal with the document variations expected in an organization serving borrowers across the nation.

The ideal solution needed to provide a seamless interface to this current capture infrastructure. This would greatly simplify the implementation by allowing the existing interfaces to both front-end scanning and back-end image storage to be largely unaffected by the addition of the recognition technology.

Prior to the installation of the new recognition components, a large team would manually classify incoming documents into a moderately broad range of categories or Document Groups. Once these documents had reached the enterprise content management system, a team of underwriters would review, manually enter data, and process the loan.

Limitations of this approach included:

>>Heavy reliance on the skills of the people manually classifying documents and extracting data. Error rates varied from operator to operator. Thus, a loss of a skilled operator for any reason had a negative impact.

>>Time is of the essence in any mortgage-processing environment. Using a human-centric approach meant that processing times were proportional to staff availability at any given moment.

>>People tend to be more expensive than computers and software.

>>Regulatory bodies as well as this originator would have preferred a greater granularity in the way documents were classified. However, this need was outweighed by the complexity and difficulty presented when attempting to teach and maintain a group of individuals in how to classify documents among over 250 possible choices.

The new extraction system was selected after an exhaustive evaluation process. A competing solution was initially tried. However, after months of tests, it was determined that a more advanced solution was available which had a number of capabilities that surpassed other solutions previously tested or reviewed:

>>This new solution was by far the fastest technology available to read OCR mortgage documents. Pre-production technical due diligence empirically showed a system that was capable of processing approximately 1 million images per day on a single twelve-core server.

>>This solution was able to use one set of rules to process and recognize all document variations. Because of the extremely large number of documents (and variations of each), which this top five originator encounters, they required the flexibility offered by a non-template-based ADR (Automated Document Classification) and data extraction solution.

>>This solution offered pre-built mortgage logic, which “understands” the vast majority of the document types and variations that were required to be recognized. This solution allowed this originator to rapidly implement an ADR and data extraction solution for their specific needs.

The initial focus was to implement an ADR solution that supported more than 250 different document types and potentially hundreds of variations of each document type. The vast majority of the pages in a loan are now identified automatically with no human intervention. The remaining exceptions are presented to operators who either accept the first choice page type or choose an alternative.

This system is able to narrow down the page types that are lexically possible based on the text on the page. Because of this, in most cases, the operator can choose from a list of no more than five alternate page types. This reduces errors and review time in the verification process.

Upon production implementation of the ADR solution, the focus shifted to automatic data extraction. A list of more than 1500 fields was identified for the first implementation phase of data extraction. Both this project and the ADR work that preceded it were initially implemented in one of the originator’s major channels in order to ensure a wide variety of document sources and variations.

Today both of the projects described above are in full production. The amount of manual labor previously required for these tasks has been reduced significantly. Error rates are lower than the human processes that preceded implementation. The end to end processing time has been vastly reduced due to the fact that much of the human labor has now been replaced by lightning fast computer CPU cycles. Additionally, this top five originator has implemented sophisticated downstream mortgage lending business rules to take advantage of the valuable data generated by the new system.

This top five originator, like any other mortgage lender, is subject to a variety of time-sensitive requests such as internal audits. These audits require that specific data be tabulated from each loan file and reported to the appropriate entity. In some cases, the volume of loans included in these audits can reach into the tens of thousands, with a very limited response timeframe. With the system now in production, it is possible for this organization to be more agile than in the past. New data fields can be configured and tested in a few hours and a million images can now be interrogated for salient data overnight.

Additional capabilities leveraged successfully at this customer include:

>>Verification provides a list of likely document types to further increase speed of verifying exceptions.

>>Ability to customize how documents are handled based on the type of process to be conducted (e.g. origination, servicing, audit, etc.).

>>Ability to quickly recognize additional document types using the automated learning facility.

>>Database lookups and business rule logic checks to ensure the highest degree of data accuracy.

>>No scripting interface, with easily configurable rules to modify customers’ highly sophisticated ADR and data extraction processes.

>>Ability to add processor cores (including new servers) to the environment in a matter of minutes to quickly scale and meet tight deadlines or increased staffing demands.

Outcome

The project was successfully implemented and released to production on time. As a result of this experience with both the Paradatec staff and the Paradatec solution, this customer is prepared to act as a reference on behalf of Paradatec. Prospective clients are encouraged to take advantage of this opportunity.

Paradatec is rapidly approaching the significant milestone of processing 300,000,000 pages annually for this client alone. As a company, Paradatec processes several billion pages per year.

Paradatec’s solution is an advanced and unique OCR recognition technology. It utilizes neural networks technology and artificial intelligence and is able to read structured, semi-structured, and unstructured documents. It then makes ‘decisions’ about document characteristics in much the same way as a human being does— only many times faster and without human intervention.

Paradatec takes a very different approach from other OCR forms processing technologies in that it is a truly template-free design, allowing the system to easily cope with the varying layouts of each document. In performance terms, Paradatec is capable of processing thousands of documents per hour with a single processor. It provides even further scalability by offering seamless support for the latest in multi-core processor technologies and multi-server configurations.

Per Neil Fraser, Director, of US Operations, “To be chosen by such a high-profile client for a project of this size was a vote of confidence for Paradatec and our leading edge technology. I would encourage other similarly placed clients to reach out to Paradatec to setup a ‘One-Day Blind Test Challenge’. In just a day it is possible to see what this technology can do, right out of the box.”

About The Author

Mark Tinkham
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).

Paradatec Named Verified UCD Producer By Freddie Mac

Paradatec, Inc., a provider of Optical Character Recognition (OCR) solutions for mortgage file processing, announced that it is a verified technology integration vendor for Freddie Mac’s Loan Closing Advisor platform. Paradatec’s WriteUCD module was developed in accordance with Freddie Mac’s requirements for producing valid Uniform Closing Dataset (UCD) files.

Featured Sponsors:

 

 
The UCD is a common collection of data that mortgage lenders will be required to deliver digitally to Freddie Mac and Fannie Mae starting on Sept. 25, 2017. This requirement is part of the Uniform Mortgage Data Program (UMDP), an industry-wide drive to build a better housing finance system in the United States.

Featured Sponsors:

 
The WriteUCD module leverages Paradatec’s advanced OCR solution for the mortgage market to extract data from closing disclosure (CD) documents in mere seconds per page and then format that data in the required format.

According to Neil Fraser, Paradatec’s Director of US Operations, “We’re pleased to have obtained Freddie Mac validation as our clients need the assurance that they can meet the GSEs’ requirements well in advance of the September deadline. If a lender’s current loan origination system partner or document provider is struggling to produce a valid UCD file, they can sleep soundly knowing that Paradatec has them covered with our new WriteUCD module.”

Featured Sponsors:

 
Paradatec also announces the release of their new AuditUCD module for auditing UCD file content against the closing disclosure contained in the UCD file. Fraser continues, “Since we’re building the UCD file from extracted closing disclosure data, it’s just as easy for us to unpack a UCD file’s content to compare the individual data elements against the values extracted from the submitted CD to verify the integrity of both components in the UCD file. Any elements that don’t match will be flagged in our XML output for further review and resolution. Given the volume of content that will be produced and need verification with this UCD initiative, our solution is uniquely positioned to offer a high degree of automation and operator efficiency.”

About The Author

Tony Garritano
Tony Garritano is chairman and founder at PROGRESS in Lending Association. As a speaker Tony has worked hard to inform executives about how technology should be a tool used to further business objectives. For over 10 years he has worked as a journalist, researcher and speaker in the mortgage technology space. Starting this association was the next step for someone like Tony, who has dedicated his career to providing mortgage executives with the information needed to make informed technology decisions. He can be reached via e-mail at tony@progressinlending.com.

Paradatec Achieves Fannie Mae UCD Certification

Paradatec, Inc.’s new WriteUCD module was recently certified by Fannie Mae as meeting their requirements for producing valid Uniform Closing Dataset (UCD) files. This new module leverages Paradatec’s Optical Character Recognition (OCR) solution for the mortgage market to extract data from Closing Disclosure (CD) documents and then format that data in the MISMO standard required by Fannie Mae. The certification process required submitting test UCD files for multiple lending scenarios for Fannie Mae’s review, with all tests being passed successfully.

Featured Sponsors:

 

 
According to Neil Fraser, Paradatec’s Director of US Operations, “Developing this new module was an easy decision for us. Many clients are already using our solution to extract data from the TRID documents to support certain internal review and audit procedures, so since we have the logic to extract this data it made sense to create a module which formats this data per the UCD specification. Now that we’ve attained certification with Fannie Mae, our clients who work with them are assured of complying with their September 2017 UCD requirement with this new WriteUCD module.”

Featured Sponsors:

 
Paradatec also announces the release of their new AuditUCD module for auditing UCD file content against the Closing Disclosure contained in the UCD file. Fraser continues, “Again, developing this module was a logical extension to our mortgage solution. Since we’re able to build the UCD file from extracted Closing Disclosure data, it’s just as easy for us to unpack a UCD file’s content to compare the individual data elements against the values extracted from the submitted CD to verify the integrity of both components in the UCD file. Any elements that don’t match will be flagged in our XML output for further review and resolution. Given the volume of content that will be produced and need verification with this UCD initiative, our solution is uniquely positioned to offer a high degree of automation and operator efficiency.”

Featured Sponsors:

 
Paradatec’s OCR solutions offer significant efficiencies for classifying large quantities of differing document types and extracting key data elements from those documents.  In the mortgage market, these capabilities allow for quick and accurate identification of over 500 unique documents in the typical mortgage file, along with the ability to capture nearly any data element from those documents that an organization requires.

Progress In Lending
The Place For Thought Leaders And Visionaries