US 11,694,257 B2
Utilizing artificial intelligence to make a prediction about an entity based on user sentiment and transaction history
Joni Bridget Jezewski, Fairfax, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jul. 19, 2019, as Appl. No. 16/516,506.
Application 16/516,506 is a continuation of application No. 15/896,953, filed on Feb. 14, 2018, granted, now 10,360,631.
Prior Publication US 2019/0340688 A1, Nov. 7, 2019
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 40/06 (2012.01); G06Q 40/04 (2012.01); G06Q 30/0202 (2023.01); G06Q 50/00 (2012.01); G06Q 30/0201 (2023.01)
CPC G06Q 40/04 (2013.01) [G06Q 30/0201 (2013.01); G06Q 30/0202 (2013.01); G06Q 40/06 (2013.01); G06Q 50/01 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, by a device, comment information associated with a plurality of users and relating to an entity;
generating, by the device, a plurality of interim scores associated with the entity via artificial intelligence based upon the comment information;
receiving, by the device, transaction information associated with one or more of the plurality of users,
the transaction information relating to the entity;
determining, by the device, correlations between the plurality of interim scores associated with the comment information and the transaction information by using at least one of:
a correlation clustering method,
a Pearson's product-moment coefficient method,
an Anscombe's quartet method, or
a Spearman's rank-correlation coefficient method;
applying, by the device, weights to the plurality of interim scores based upon the correlations;
generating, by the device, a prediction about a future stock price of the entity based on the weighted plurality of interim scores;
storing, in a relational database to reduce redundancy, the weighted plurality of interim scores and the transaction information,
the relational database being organized in columns and tables via a data normalization method; and
causing, by the device, an action to be taken based on the prediction about the future stock price of the entity,
the action including one or more of:
automatically providing, to a client device, a notification indicating the future stock price of the entity,
automatically sending an instruction to a server to buy or sell a stock associated with the entity, or
automatically causing a calculation of a future value of a financial portfolio to be generated.