The "American Dream" has forever included land and home ownership. But unfortunately, that dream was formally kept out of reach of many people by the way of Discriminatory Restrictive Covenants included in land and property records. These covenants explicitly prevented the transfer of ownership to people based on race, color, religion, national origin, and gender.
In 1968, the Fair Housing Act made it illegal to include such covenants in new deeds or advertisements. The law also makes existing covenants illegal and unenforceable but it did not take any measures to remove the language from existing documents. These covenants still exist in millions of legal documents across all 50 states.
Many states have begun the process of formally mapping and identifying these covenants, but only California has specifically required Discriminatory Restrictive Covenants to be removed and the documents refiled via a Restrictive Covenant Modification.
This begs the question…what is the best way to identify documents that need to be updated in the most efficient manner possible?
Removing these clauses requires meticulous work, and the technical complexities are significant. It requires sifting through mountains of historical documents, each with its own idiosyncrasies of language and formatting. Identifying clauses amidst legalese and outdated terminology is like searching for a needle in a haystack.
Furthermore, these covenants often lack clear definitions, and ambiguous wording makes interpretation very challenging. For example, a seemingly straightforward statement like "Whites only" was often implemented in convoluted ways. Additionally, words such as "white" and "black" may refer to the names of people and places and require no action at all.
Adding to this complexity is the high volume of documents in question. California has millions of properties, each with the potential to contain these discriminatory clauses. Digitizing and analyzing this data at scale necessitates sophisticated technology and skilled professionals.
Finding the documents that potentially contain the offending terminology is the first piece of the puzzle. This requires Optical Character Recognition (OCR).
Identifying the potential restrictive covenants alone, does not offer counties what they need to handle these terms efficiently and effectively. To make this OCR data truly powerful, it needs to be paired with the following features:
Machine learning and advanced vision models
Identification of terms that have poor quality and aren't read perfectly by the system
Elimination of false positives to reduce the number of documents that must be reviewed for resubmission
Workflow design to accommodate the different needs of every county (one or multiple reviews by the County Counsel or other management members)
The ability to review/add index data to aid in searchability
The ability to easily deploy the solution to all users who will be tasked with the review process
Ability to update search terms and exclusion terms based on lessons learned during ongoing review
The ability to handle documents from different timeframes in different ways
Extract has a long history of providing document management solutions that can accommodate all of the needs above and more.
About the Author: Rob Fea
Rob spent 12 years partnering with IT teams and clinicians at major hospitals and clinics worldwide during his tenure on the technical services team at Epic. He supported Epic's Phoenix product, playing a major role in project kickoffs, installation, data conversions, ongoing support, and optimization. Rob watched the Phoenix customer base expand from 0 to 55 live and installing transplant organizations. This experience gave Rob expansive insight into the healthcare world, especially the solid organ transplant industry. Rob has spent countless hours on the floor in transplant departments observing multidisciplinary visits, committee review meetings, data entry, data trending, reporting, medication dosing, and more.