Robotics, AI, and Machine Learning Power Rocket’s Pathfinder Mortgage Guideline Search

The innovative tool leverages generative AI technology to provide one source of truth for loan officers and underwriters, helping buyers purchase their new home with speed and certainty

Rocket Mortgage, America’s largest retail mortgage lender and a part of Rocket Companies announced continued advancements to its Pathfinder tool, an AI and machine learning-powered search engine used by mortgage bankers, brokers and underwriters to confidently find the answers to complicated qualification or loan processing questions. Pathfinder’s proprietary technology is used by more than 40,000 housing professionals, providing one source of truth that cuts through mortgage processing complexities to help clients achieve their dream of homeownership.

Recommended AI News: Split Payments Innovator Anyday Selects ComplyAdvantage For Award-Winning Customer Screening and Monitoring Solution

The tool catapults the mortgage industry into the information age. In the same way that smart phones put all the world’s knowledge in their users’ pockets, Pathfinder ensures those who originate and process home l**** have all the information needed to facilitate the American dream at their fingertips. Instead of thumbing through emailed guideline updates, printed reference pages, handwritten notes or tapping into their personal experience, in mere seconds loan officers can search Pathfinder’s unmatched 400,000 pieces of content.

“Pathfinder has been an invaluable tool for curating complex data and transforming it into knowledge engineering. This technology, and others that leverage advancements in AI and machine learning, are truly evolving how we can facilitate homeownership,” said Brian Woodring, Chief Information Officer of Rocket Mortgage.

Perennial technology leaders, Rocket Mortgage was the first lender to release a searchable home loan knowledge database three years ago – simplifying the nuanced home loan process.  At the time, Rocket started working on a machine learning framework for natural language processing – which increased Rocket’s speed and efficiency in answering client questions without additional follow up by 20%. Rocket then continued to advance its technology and now uses its own custom Google AI search, which helped Pathfinder surpass the previous milestone by another 9%.

Rocket is also testing a new AI chat interface in Pathfinder to help mortgage bankers and brokers answer client questions. This test has preliminarily resulted in a 69% increase in speed to resolution, compared to the current process. With that success, Rocket is supercharging the Pathfinder experience using large language models (LLM) and is currently adding more than 3,300 new loan scenarios to help loan officers provide resolutions for their clients with speed and confidence. All told, Pathfinder collects 75,000 data points each day that Rocket can use to train the tool to be even more effective.

With the easy access to mortgage data, a mortgage banker, broker or underwriter who just joined the industry has access to a collection of knowledge that would usually take decades to accumulate. To illustrate just how useful it is, page views and automated actions – which help loan officers find the best option based on a client’s specific financial situation – account for more than 1.5 million interactions with Pathfinder each month. Loan officers can lean on Pathfinder’s technology to easily uncover the benefits of every loan program, while they focus on the important things that only humans can do – like building relationships with clients.

This announcement marks the first of many advancements for Pathfinder that will enhance the banker, broker and client experience through new, innovative generative AI technology.

Recommended AI News: Kount, an Equifax Company, Expands International Presence

Forward Looking Statements

Some of the statements contained in this document are forward-looking statements within the meaning of Section 27A of the Securities Act of 1933, as amended, and Section 21E of the Securities Exchange Act of 1934, as amended. These forward-looking statements are generally identified by the use of words such as “anticipate,” “believe,” “could,” “estimate,” “expect,” “intend,” “may,” “plan,” “potential,” “predict,” “project,” “should,” “target,” “will,” “would” and, in each case, their negative or other various or comparable terminology. These forward-looking statements reflect our views with respect to future events as of the date of this document and are based on our management’s current expectations, estimates, forecasts, projections, assumptions, beliefs and information. Although management believes that the expectations reflected in these forward-looking statements are reasonable, it can give no assurance that these expectations will prove to have been correct. All such forward-looking statements are subject to risks and uncertainties, many of which are outside of our control, and could cause future events or results to be materially different from those stated or implied in this document. It is not possible to predict or identify all such risks. These risks include, but are not limited to, the risk factors that are described under the section titled “Risk Factors” in our Annual Report on Form 10-K, Current Reports on Form 8-K, and other filings with the Securities and Exchange Commission. These factors should not be construed as exhaustive and should be read in conjunction with the other cautionary statements that are included in this document and in our SEC filings. We expressly disclaim any obligation to publicly update or review any forward-looking statements, whether as a result of new information, future developments or otherwise, except as required by applicable law.

Recommended AI News: ThirdEye Announces Worldwide Decentralized Augmented Reality (AR) 3D Social Network for Metaverse

[To share your insights with us, please write to sghosh@martechseries.com]