This report is available exclusively to subscribers of Inman Intel, a data and research arm of Inman offering deep insights and market intelligence on the business of residential real estate and proptech. Subscribe today.
Document automation platform Ocrolus has released a new solution designed specifically for mortgage lenders to help them automate their workflow, including income calculations for gig workers, the self-employed and other non-traditionally employed borrowers.
The enhanced dashboard for mortgage lenders combines three Ocrolus solutions (Classify, Capture and Analyze) which index documents, extract information from them and streamline income calculations, providing “an objective and standardized approach to evaluating the borrower’s income, resulting in increased confidence in lending decisions and reduced risk of human error,” the company said.
Ocrolus says its automated review and analysis of borrower-supplied mortgage documents provides “full-stack capabilities,” for mortgage lenders, helping them capture key data fields, detect fraud and analyze cash flows.
“Manual document processing and income analysis create a bottleneck in the origination process,” said Ocrolus Chief Operating Officer Vik Dua, in a statement. “With Ocrolus’ enhanced mortgage offering, we’re empowering lenders with accurate document analysis to help reduce processing time, mitigate risk and maximize profit margin on every single loan.”
The new mortgage offering integrates with any workflow or loan origination system through the Ocrolus dashboard or an application programming interface (API) connection, and provides simplified note and comment tracking for loan officers and processors.
The new mortgage offering follows on the heels of a fully automated document processing solution, Instant, Ocrolus debuted this summer as a complementary service to its Complete offering, which also provides human data verification for lower quality documents.
An AI-powered, machine-only solution, Instant provides insights within seconds that lenders can use to make underwriting decisions.
“Ocrolus has analyzed hundreds of millions of pages of financial documents, using AI working in tandem with Human-in-the-Loop (HITL) data validation,” Ocrolus co-founder and CEO Sam Bobley said in announcing the launch of Instant. “Thanks to our massive volume of training data, our automation capabilities have reached a point where we are thrilled to debut a machine-only offering with greater coverage and accuracy than any other software product in the market.”
In May, Ocrolus furthered its claim to be a leader in AI-driven financial document automation by announcing that it had integrated OpenAI’s text embeddings to better process bank statements, pay stubs and mortgage applications without human involvement.
Text embeddings, which measure the relatedness of text strings, are commonly used for classification, search and recommendations, according to OpenAI, the company behind the ChatGPT. Ocrolus also uses subsystems from Amazon, Google and its own proprietary deep learning architectures to help mortgage lenders and other financial services companies automate the capture, classification, and analysis of documents used to make lending decisions.
Based in New York, Ocrolus announced an $80 million Series C funding round in 2021 that valued the company at more than $500 million.
Clients include cloud banking software provider Blend, PayPal, Plaid, Enova, Bluevine and SoFi. This year alone Ocrolus has signed BSI Financial, Bluepoint Mortgage, Cion Digital, City Lending, Greenbox Loans, Integra Auto, Kuboon, Lentegrity, NTropy and Truv as clients.
Get Inman’s Mortgage Brief Newsletter delivered right to your inbox. A weekly roundup of all the biggest news in the world of mortgages and closings delivered every Wednesday. Click here to subscribe.