US 11,720,937 B2
Methods and systems for dynamic price negotiation
Jeffrey Rule, Chevy Chase, MD (US); and Kevin Osborn, Newton Highlands, MA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jun. 22, 2020, as Appl. No. 16/907,843.
Prior Publication US 2021/0398175 A1, Dec. 23, 2021
Int. Cl. G06Q 30/00 (2023.01); G06Q 30/0283 (2023.01); G06N 20/00 (2019.01); G06F 16/9535 (2019.01); G06Q 30/0207 (2023.01); G06Q 50/18 (2012.01)
CPC G06Q 30/0283 (2013.01) [G06F 16/9535 (2019.01); G06N 20/00 (2019.01); G06Q 30/0236 (2013.01); G06Q 50/188 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for negotiating a price of a product for a user, the method comprising:
obtaining, by one or more processors, an identification of the user from a user device associated with the user, wherein:
the identification of the user comprises one or more of an actual name, a social security number, or a phone number associated with the user; and
the user device is one of:
a near-field communication (NFC) card, wherein the identification of the user is obtained from a scan of a component of the NFC card by an electronic reader; or
an electronic mobile device, wherein the identification of the user is obtained from a scan of a graphical component by a camera of the electronic mobile device;
determining, by the one or more processors, whether the user is authenticated by comparing the identification of the user with a prestored identification;
upon determining that the user is authenticated, obtaining, by the one or more processors, raw data from one or more social networks associated with the user, wherein the raw data comprises one or more of:
retweets;
list or group memberships;
quantity of spam or dead accounts following the user; or
degree of influence of people who retweet user;
generating, by the one or more processors, social influence data associated with the user based on the raw data, wherein the social influence data comprises one or more of:
a net promoter score;
a social ranking;
a social reach;
an amplification score; or
a network impact;
based on the identification of the user, obtaining, by the one or more processors, purchase parameter data associated with the user, wherein the purchase parameter data comprises one or more of:
a credit score associated with the user; or
an income range of the user;
determining, by the one or more processors, using a trained machine learning model, a user-specific price of a product based on the purchase parameter data of the user and the social influence data of the user, wherein:
the trained machine learning model is trained, using supervised, un-supervised, or semi-supervised learning, based on (i) training user data that includes information regarding purchase parameter data and social influence data associated with persons other than the user; and (ii) training price data that includes user-specific prices for one or more products associated with the persons other than the user, to learn relationships between the training user data and the training price data, such that the trained machine learning model is configured to determine a user-specific price of a product for a user upon input of the purchase parameter data of the user and the social influence data of the user; and
the trained machine learning model is configured to utilize principal component analysis; and
the determined user-specific price of a product is stored for a period of time and expires after the period of time, and during the period of time, the determined user-specific price of the product is available for further analysis; and
transmitting, to the user, a notification indicative of the user-specific price.