Patent describes way to personalize domain search results.
The U.S. Patent and Trademark Office has granted patent number 10,693,837 (pdf) to Verisign (NASDAQ: VRSN) for System for and method of ranking domain names based on user properties.
The patent describes a way to use personal information about the registrant to personalize domain search results. From the patent:
Some embodiments provide novel approaches for ranking (e.g., sorting) domain names on a personalized basis. Such personalization may be specific to an individual user, such as a potential registrant. The domain names may be ranked according to a prediction of how interested the particular user might be in registering such names. Note that, because the rankings are personalized, two potential domain name registrants may be given different presentations/orderings of the same set of domain names.
In more detail, some embodiments employ machine learning techniques based on properties of the user, such as gender, hobbies, country of residence, etc., as well as properties of domain names, e.g., length, language, top-level domain, etc., as well as contextual properties, e.g., the potential forum of the sale. The rankings may take into account prior domain name purchasing behavior of individuals that are determined to be similar to the user. Such embodiments provide for more relevant names being more prominently presented to the potential registrant, thus increasing overall registrations for, e.g., a registrar.
I believe some registrars already do certain elements of this when presenting search results.
Verisign applied for the patent in 2017. The patent names Swapneel Sheth, Director of Research Engineering, and Andrew West, Principal Research Scientist, as inventors.