US 11,915,290 B2
Systems and methods for determining and leveraging geography-dependent relative desirability of products
Jason Hoover, Grapevine, TX (US); Avid Ghamsari, Frisco, TX (US); Qiaochu Tang, The Colony, TX (US); Geoffrey Dagley, McKinney, TX (US); and Micah Price, Plano, TX (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Apr. 20, 2020, as Appl. No. 16/853,126.
Prior Publication US 2021/0326957 A1, Oct. 21, 2021
Int. Cl. G06Q 30/00 (2023.01); G06Q 30/0601 (2023.01); G06Q 30/0204 (2023.01)
CPC G06Q 30/0627 (2013.01) [G06Q 30/0205 (2013.01); G06Q 30/0639 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for regulating vehicle stock, the method comprising:
receiving, by one or more processors, via a graphical user interface associated with a user, a query indicative of one or more characteristics of one or more purchasable vehicles at a location of a merchant;
receiving, by the one or more processors, queries data including one or more queries indicative of one or more characteristics of the one or more purchasable vehicles received from additional users;
receiving, by the one or more processors from a merchant database, transaction data including a quantity of the one or more purchasable vehicles that were purchased or attempted to be purchased by the additional users, wherein the transaction data is obtained from a database of an issuer, wherein the issuer is a financial service entity;
assigning, by the one or more processors, using at least one trained machine learning model, a desirability value to each of the one or more purchasable vehicles based on the at least one trained machine learning model learning relationships between the transaction data, the queries data, and the one or more characteristics of the one or more purchasable vehicles;
determining, by the one or more processors, an availability at the location of the merchant for each of the one or more purchasable vehicles assigned a desirability value;
assigning, by the one or more processors, a likelihood value for each of the one or more available vehicles assigned a desirability value, wherein the likelihood value is a likelihood that the user purchases each of the one or more available vehicles assigned a desirability value and is based on one or more of a user preference set by the user or a user financial status and the desirability value in comparison to a threshold desirability value, the threshold desirability value determined by the issuer or the user;
transmitting, by the one or more processors, to the user, for display via the graphical user interface, a recommendation to purchase an available vehicle assigned a highest likelihood value and a desirability value below the threshold desirability value;
receiving, by the one or more processors, additional transaction data from a purchaser info database, the additional transaction data including whether the user purchased or failed to purchase the recommended available vehicle; and
transmitting to the user, by the one or more processors, a second recommendation to purchase a second available vehicle, the second recommendation dynamically determined based on the at least one trained machine learning model assigning an updated desirability value for the second recommendation based on the additional transaction data.