US 11,861,694 B1
Financial autopilot
Nathan Mahoney, New Braunfels, TX (US); Luis Daniel Silva, San Antonio, TX (US); Gunjan C. Vijayvergia, San Antonio, TX (US); and Jason Paul Hendry, Selma, 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 Aug. 24, 2021, as Appl. No. 17/410,473.
Application 17/410,473 is a continuation of application No. 16/585,519, filed on Sep. 27, 2019, granted, now 11,127,075.
Claims priority of provisional application 62/738,544, filed on Sep. 28, 2018.
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 40/02 (2023.01); G06Q 40/12 (2023.01); G06N 20/00 (2019.01)
CPC G06Q 40/02 (2013.01) [G06N 20/00 (2019.01); G06Q 40/12 (2013.12)] 18 Claims
OG exemplary drawing
 
1. A method implemented by a data processing system, comprising:
receiving training data including (i) transaction histories of a plurality of users during a specific period of time, and (ii) for each of the plurality of users, data specifying unexpected expenses that occurred to the respective user during the specific period of time;
training a neural network to predict an unexpected expense for a given transaction history using a supervised learning technique based on the training data, wherein the neural network is configured to receive as input the given transaction history and to process the input to generate an output that specifies a specified expense for the given transaction history, wherein the neural network comprises a plurality of artificial neurons that are connected through edges and are aggregated into a plurality of neural network layers comprising at least an input layer and an output layer, wherein each of the edges is configured to transmit a signal from one artificial neuron to another artificial neuron, and wherein an output of each of the plurality of artificial neurons is computed by a specified function of a sum of inputs of the artificial neuron in accordance with a plurality of weights;
setting values of the plurality of weights based on the training of the neural network;
receiving new data indicating a list of historic transactions of a particular user from a plurality of financial institutions;
processing, by the data processing system, the new data using the plurality of artificial neurons in the trained neural network in accordance with the values of the plurality of weights to identify at least one specified expense for the particular user, wherein the artificial neurons in the input layer are configured to receive the new data as input and the artificial neurons in the output layer are configured to generate a new output that identifies the at least one specified expense;
determining a plan to account for the at least one specified expense; and
automatically transferring, by the data processing system, an amount from a first account of the particular user to a second account of the particular user based on the plan.