US 12,067,570 B2
System, method, and computer program product for predicting a specified geographic area of a user
Mahashweta Das, Sunnyvale, CA (US); and Hao Yang, San Jose, CA (US)
Assigned to Visa International Service Association, San Francisco, CA (US)
Appl. No. 16/971,798
Filed by Visa International Service Association, San Francisco, CA (US)
PCT Filed Feb. 23, 2018, PCT No. PCT/US2018/019308
§ 371(c)(1), (2) Date Aug. 21, 2020,
PCT Pub. No. WO2019/164495, PCT Pub. Date Aug. 29, 2019.
Prior Publication US 2020/0402057 A1, Dec. 24, 2020
Int. Cl. G06Q 20/40 (2012.01); G06N 20/00 (2019.01); G06Q 30/0211 (2023.01); H04W 4/029 (2018.01)
CPC G06Q 20/4015 (2020.05) [G06N 20/00 (2019.01); G06Q 20/4093 (2013.01); G06Q 30/0211 (2013.01); H04W 4/029 (2018.02)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, with at least one processor, transaction data associated with a plurality of transactions involving a plurality of users and a plurality of merchants during a predetermined time interval;
generating, with at least one processor, a geographic area prediction model;
determining, with at least one processor, a verified geographic area of a plurality of geographic areas for each user of the plurality of users;
determining, with at least one processor, transaction data associated with a plurality of transactions involving each user of the plurality of users for each feature vector parameter of a plurality of feature vector parameters, wherein determining the transaction data comprises determining each feature vector parameter of the plurality of feature vector parameters for each geographic area of the plurality of geographic areas;
training, with at least one processor, the geographic area prediction model based on the plurality of feature vector parameters for the verified geographic area for each user of the plurality of users;
validating, with at least one processor, the geographic area prediction model based on the plurality of feature vector parameters for the verified geographic area for each user of the plurality of users; and
repeating over a plurality of time intervals:
generating, with at least one processor, a prediction that a user will conduct a transaction in a geographic area based on the geographic area prediction model;
communicating, with at least one processor, an offer to the user based on the prediction;
receiving, with at least one processor, new training data by processing a transaction conducted by the user in the geographic area within a predetermined amount of time from the offer being communicated to the user; and
updating, with at least one processor, the geographic area prediction model based on the new training data.