Company: First American Data and Analytics, Santa Ana, CA
Company Description: First American Financial Corporation (NYSE: FAF) is a leading provider of title insurance, settlement services and risk solutions for real estate transactions that traces its heritage back to 1889. First American also provides title plant management services; title and other real property records and images; valuation products and services. For more information visit: http://www.firstam.com/.
Nomination Category: New Product & Service Categories - Content
Nomination Sub Category: Aggregation Platform
 Nomination Title: First American Data and Analytics' CovenantGuard
- Which will you submit for your nomination in this category, a video of up to five (5) minutes in length about the nominated new or new-version product or service, OR written answers to the questions for this category? (Choose one):
Written answers to the questions
- If you are submitting a video of up to five (5) minutes in length, provide the URL of the nominated video here, OR attach it to your entry via the "Add Attachments, Videos, or Links to This Entry" link above, through which you may also upload a copy of your video.
- If you are providing written answers for your submission, you must provide an answer to this first question: If this is a brand-new product, state the date on which it was released. If this is a new version of an existing product, state the date on which the update was released:
New platform, released in April 2022.
Executive Summary
The United States Fair Housing Act of 1968 made it unlawful to refuse to sell or rent to a person because of that person’s race, color, disability, religion, sex, familial status, or national origin. States such as California have similar or much more expansive laws governing housing discrimination. Despite the legislation, illegal restrictive covenants declaring to whom a property may or may not be sold (or rented) continued to be inserted in real estate documents (examples in the attachment).
As of April 2022, First American Data & Analytics has AI-driven technology to scan for and identify illegal restrictive covenants in any document recorded in the United States.
Issue
Illegal restrictive covenants (RC) are found in recorded property documents going back over a century. The language is inconsistent and can be found in a variety of document types which all have different content structure, and which may be handwritten. Identifying documents that contain RC among the billions that have been recorded is like finding a needle in a haystack. However, this is exactly what is required to redact the RC and re-record the documents so that the illegal and offensive language is not propagated in future recordings.
How does the industry, with limited staffing and technology resources and an inventory of billions of documents, find documents with restrictive covenants and then redact the illegal language?
- If you are providing written answers for your submission, you must provide an answer to this second question: Describe the features, functions, and benefits of the nominated product or service (up to 350 words):
Total 279 words used.
Solution
First American Data & Analytics leveraged its document, data, and technical expertise to develop machine learning, AI models, and OCR extraction to recognize a specific set of racially focused RC keywords and phrases in any document. A flag was set if RC was detected. Separate processes, like automatically inserting a cover sheet as the document is delivered to the customer stating that such language was identified, could then be driven from the flag.
Content from document images, public record databases, proprietary keyword/phrases, and machine learning models had to work in conjunction for the identification of RC to be successful. The First American team took a major leap forward when they created the Artificial Intelligence (AI) models for this project. They then combined the models with the OCR and data extraction processes already in place, some of which are patented. Similar AI-driven data solutions have previously won two Gold ABA awards.
Content was also created and aggregated back into the platform. Statistics on the number of documents processed, number where RC was found, and RC phrases identified are just some of the actions tracked and available for report generation. The machine learning models also use their own results to feed back into the system for model improvement.
The entire process of scanning, identifying, and flagging is done seamlessly in the background and in a fraction of a second. It requires no user intervention which alleviates the need for the customer to manually read real estate documents searching for RC.
Ultimately, this is one small step towards correcting an injustice in the public record and aligning it with the law that has been in place for over half a century.
- If you are providing written answers for your submission, you must provide an answer to this third question: Outline the market performance, critical reception, and customer satisfaction with the product or service to date. State monetary or unit sales figures to date, if possible, and how they compare to expectations or past performance. Provide links to laudatory product or service reviews. Include some customer testimonials, if applicable (up to 350 words):
Total 98 words used.
Results
The project to scan the 8 billion documents housed in the First American Data & Analytics document repository for RC was completed in April 2022.
The content aggregation platform described here is the foundation of CovenantGuard, a workflow product used by counties to manage the task of identifying, redacting, and re-recording historical public record property documents. Without CovenantGuard, those in the industry would not have the time or resources to manually identify documents with illegal RC.
Please see the press release from an early adopter and their testimonial on the platform and the video describing the platform.
- You have the option to answer this final question: Reference any attachments of supporting materials throughout this nomination and how they provide evidence of the claims you have made in this nomination (up to 250 words):
Total 17 words used.
Please see that attached press release, video and written nomination with footnotes and examples of restrictive covenants.
| Attachments/Videos/Links: |
|---|
|
