US 11,935,060 B1
Systems and methods based on anonymized data
John Gibson, San Antonio, TX (US); and Linqiu Wu, San Antonio, TX (US)
Assigned to United Services Automobile Association (USAA), San Antonio, TX (US)
Filed by United Services Automobile Association (USAA), San Antonio, TX (US)
Filed on Jun. 30, 2020, as Appl. No. 16/917,296.
Int. Cl. G06Q 20/40 (2012.01); G06F 18/2413 (2023.01); G06F 21/62 (2013.01); G06N 20/00 (2019.01)
CPC G06Q 20/4016 (2013.01) [G06F 18/24147 (2023.01); G06F 21/6254 (2013.01); G06N 20/00 (2019.01); G06Q 20/4015 (2020.05)] 16 Claims
OG exemplary drawing
 
1. A system comprising:
a communication interface;
one or more processors coupled to the communication interface; and
a memory storing a plurality of vectors, a predictive model, and instructions that, when executed by the one or more processors, cause the one or more processors to:
implement a secure service application controller comprising a service layer configured to:
receive, via the communication interface, transaction data of a financial transaction associated with a user, wherein the transaction data comprises a transaction amount and merchant information; and
anonymize the user transaction data, wherein the anonymized user transaction data excludes demographic information of the user;
wherein the memory storing the instructions, that when executed by the one or more processors, further cause the one or more processors to:
receive, via the communication interface from the secure service application controller, the anonymized transaction data of the user;
categorize the anonymized transaction data into a plurality of dimensions for the user, wherein the categorizing the anonymized transaction data further comprises categorizing the anonymized transaction data based on a merchant category code associated with the information of the merchant;
generate a user vector based on the plurality of dimensions;
reduce the user vector by reducing a plurality of vector components of the anonymized transaction data, wherein the reducing the plurality of vector components is based on reduced dimensions of the plurality of dimensions and a plurality of variables representative of a plurality of categories associated with the predictive model;
identify one or more closest vectors from the plurality of vectors for the user using the reduced user vector, wherein the identified one or more closest vectors are associated one or more users or user groups, wherein the secure service application controller is configured to receive multi-user transaction data of a plurality of users via the communication interface and to anonymize the multi-user transaction data, and wherein the transaction data of the user and the multi-user transaction data of the plurality of users are anonymous data that do not comprise or are not linked to identification information of the user and the plurality of users, and wherein the one or more closest vectors is not based on matching by the demographic information of the user and the plurality of users;
generate a notification associated with the transaction data to the user based on the one or more closest vectors; and
transmit, via the communication interface, the notification to the secure service application controller;
wherein the secure service application controller is further configured to:
associate the notification with the user; and
communicate or push the notification to a device of the user.