Proptech Home Loan publishes the “first of many” APIs on its existing lending platform, designed to automate document validation and data mining in the lending process. The latest technology, dubbed Roostify Document Intelligence Service (RDI), will use AI to classify, validate and extract data from mortgage-related documents.
Roostify CEO and Co-Founder Rajesh Bhat told FinLedger that RDI works as a microservice API, so it can be integrated into any stage of the loan process that works for a lender, whether Roostify is part of it. to the lender’s tech stack or not.
Development teams within a lender’s business can implement the capabilities however they want and configure them based on their current digital experience, technology stack, and use case, Bhat explained. .
The technology can also give users automatic feedback when uploading incorrect or ineligible documents and report errors before they become a data entry error.
For example, if a borrower downloads their bank statements, the data extracted can identify a large deposit that would require a letter of explanation. Once a large deposit is flagged, a task can be automatically created for the borrower that explains what they need, why, and how to provide the required information. A super useful tool, given that the technology can trigger extra steps if needed in what would typically be a paper trail.
“The way we use Roostify’s Document Intelligence service is just one example of a use case,” Bhat told FinLedger. “Because it is an API, it can be integrated anywhere in the lending process and support many use cases that benefit from the automated identification and extraction of data contained in the lending process. ‘set of mortgage documents’.
A number of proptechs are working on a possible fully digital lending documentation experiment (see, or), but Bhat sees key differences in the mission of the San Francisco-based company.
“This ease of integration at every step and the ability to transfer the extracted information throughout the process really sets it apart. What also sets it apart is that it is already increasing FI scores, ”Bhat said.
Add to this the fact that the service already supports all major income verification documents and bank statements – and is constantly updated with new documents supported, including assets and debts, identity and other mortgage documents. Even in its early stages of training AI models, it already turns out that FI scores are between 0.83 and 0.99.
Roostify’s latest launch came on the heels of a huge year not just for Roostify, but for the housing and lending industry in general. In 2020 alone, Roostify saw a 250% increase in the number of applications submitted through its system and processed just under 1.5 million loan applications through its current platform.
Technology currently powers digital mortgage platforms of, TD Bank, Guild Mortgage, and more, allowing different lenders to bring in data and information from online sources that then tailor the home buying process. They also offer a home equity platform for home equity loan applications and HELOCs under the same umbrella.
In January, proptech raised a $ 32 million Series C round, bringing Roostify’s total funding to $ 65 million at the start of the new year. At the time, Roostify suggested that their final cash injection would go to investing in AI – now they’re keeping that promise.
“To thrive in a digitally driven world, mortgage lenders need critical digital transformation initiatives, such as cloud-based technology, self-service solutions for consumers, and meaningful AI deployments.” , Bhat said. “We see the Document Intelligence Service as a very important first step in this process, and more broadly, our API platform as the basis for future developments. “