Resources

Newsroom

Back to Media & Press Releases
Media

AI Foundry Announces Mortgage Document Model

Mreport

The mortgage industry has been quick to look towards Artificial intelligence (AI) to streamline its processes and efficiency. But the question most lenders face today is how can they adopt this technology and utilize it optimally?

MReport
July 12, 2019

AI Foundry, an artificial intelligence (AI) platform company, recently announced the launch of its mortgage document model, adding new functionality to its Cognitive Business Automation Platform. According to AI Foundry, it incorporates the "latest in AI, machine learning and machine vision to deliver a higher level of automated classification and data extraction capabilities."

"This document model capability will enable the mortgage industry to use AI to replace multi-week manual processes, so that mortgages can be processed from 'application to underwriting' in days, not weeks."

“The model enables any lender to upload its loan application material and in return receive fully indexed and extracted data within seconds. The model delivers 95 percent accuracy and was trained on more than 100,000 mortgage documents, 300 document types and 2,000 data extractions to date, using both cognitive and deep neural network techniques,” said Peter Piela, Ph.D., Head of Solution Development at AI Foundry. “The percentage of accuracy using our vision technology is comparable to human manual processes, while legacy text classification approaches fall well short of this at roughly 80 percent accuracy. The impact of using our document model means significant time savings for the lender and the replacement of expensive manual processes with far more efficient automated ones.

“In addition to the document model, the platform contains a powerful rules engine that allows clients to create intelligent robotic agents to automatically monitor completeness, integrity and compliance. The rules engine enables users to make actionable inferences that trigger remedial events early in the document-processing and exception-handling phases, thereby reducing overall cycle time and the cost of remediation,” added Piela.

AI Foundry’s plan is to make the document model available to customers as part of the Cognitive Business Automation Platform, so they can use the existing model as well as augment the capabilities of the base model to solve specific mortgage workflow processes.

AI Foundry has been selected to present and demonstrate this new technology at the VentureBeat Transform Showcase Expo, July 10, 2019 in San Francisco, California.

The mortgage industry has been quick to look towards Artificial intelligence (AI) to streamline its processes and efficiency. But the question most lenders face today is how can they adopt this technology and utilize it optimally? 

At MReport's webinar titled “Intelligent Lending: The Rise of AI”, presented by AI Foundry, a panel of experts including—Stephen Butler, Founder and President of AI Foundry; Peter Piela, Head of Solution Development at AI Foundry; Rocky Stubbs, Head of Consumer Direct and Digital Mortgage Lending at Flagstar Bank; Rick Bechtel, EVP of Head of U.S. Mortgage Banking at TD Bank, and Robert Bush, SVP, Senior Strategy Manager, Citizens Bank—not only answered this question but also gave real-life case-studies of how mortgage institutions were adopting AI to improve their processes as well as cost-efficiency.

Opening the proceedings, Stephen Butler shared his insights into the need for adoption of technology enablers such as AI to make the mortgage industry ready for the future. He also listed some key concerns that organizations grapple with such as where to start the journey, how to execute the technology as well as the role of digital assistants in the future of mortgage. 

Addressing the approval times taken for loans, Butler said, “with the use of AI, one-day approvals could be the norm within five years compared to the current norm of three weeks.”

The panel was moderated by Peter Piela. He talked about how AI can create seamless lending experiences using the exponential data that is available in digital format. Though AI is in its nascent stages in many aspects, he said that “it is changing the way we do everything.”

Piela touched upon the use of mathematical and neural networks such as Machine Learning and Deep Learning to deliver promising results on a wide range of problems faced by the mortgage industry. He also spoke about the barriers to the adoption of AI on account of a lack of proven success, and the difficulty in being able to make a clear business case. Social concerns such as privacy and the shortage of expert staff that have a deep understanding of AI act as impediments to the adoption of AI, he noted.

Speaking of the impact of voice technology, Rocky Stubbs pointed out that out of a national survey of 1,000 consumers, 90 percent are aware of the technology, and 72 percent have used voice technology. “It’s an exciting time for the industry. We are rapidly moving from an era of product comparisons to an actual intelligent recommendation process,” he said.

Rick Bechtel elucidated on the Encompass platform, an all-in-one system that consolidates digital processes on a single ecosystem—which helped increase TD's overall agility and enabled faster ability to audit in-process loans and cut down on the time consumed in product deployments.

“Historically, TD was slow to introduce digital solutions in the mortgage arena. As a result, we could not simply begin launching and integrating these technologies–we had to build the foundation in order to deploy digital offerings that would be meaningful to our customers and employees,” Bechtel said.

Addressing some key questions regarding the adoption of AI, Robert Bush, spoke about how organizations can navigate through the process of AI adoption. “Focus on current business challenges across end-to-end experience and then look where AI can be a solution to increase the likelihood of getting AI’s benefits and ensure a better buy-in from stakeholders,” Bush said. Citizens Bank is currently implementing an AI use case in collections for its Consumer Lending business and will shortly work towards implementing this in their mortgage business.

view article online +