Methods and system for providing a vehicle recommendation

Patent metadata

Field	Value
Publication number	US-11282127-B2
Application number	US-201916711798-A
Country	US
Kind code	B2
Filing date	Dec 12, 2019
Priority date	Dec 12, 2019
Publication date	Mar 22, 2022
Grant date	Mar 22, 2022

Abstract

A computer-implemented method for determining a reward associated with one or more transactions of a user may comprise obtaining travel data of the user via a device associated with the user, wherein the travel data includes travel dates of the user; obtaining, via one or more processors, exchange rate data based on the travel data of the user; determining, via the one or more processors, a value of the reward associated with the one or more transactions of the user during the travel dates based on the exchange rate data; transmitting, to the user, a notification indicative of the reward associated with the one or more transactions; and causing the reward associated with the one or more transactions to be directed to a financial account associated with the user.

First claim

What is claimed is:

1. A computer-implemented method for providing a vehicle recommendation for a user, the method comprising:
obtaining, via one or more processors, transactional data of the user and prior transactional data of a plurality of users from one or more transactional entities, wherein the transactional data comprises at least one of a salary or a spending pattern of the user;
determining, via the one or more processors, a monthly payment goal of the user based on one or more inputs provided by the user via one or more interactive components of a user device, wherein the one or more inputs include a personalized monthly payment amount defined by the user;
determining, via the one or more processors, purchasing power data of the user based on the transactional data and the monthly payment goal, and prior purchasing power data of the plurality of users based on the prior transactional data, wherein the purchasing power data comprises at least a vehicle price range;
obtaining, via the one or more processors, sales data of one or more vehicles, wherein the sales data of the one or more vehicles comprises sale prices of the one or more vehicles;
training, via the one or more processors, a machine learning model having a neural network with a series of layers to map at least one variable to a value of the vehicle recommendation, wherein the series of layers includes:
an input layer to receive the prior purchasing power data and the sales data during training, and the purchasing power data during use;
an internal layer that, during training, upon receipt from the input layer, maps the prior purchasing power data to the sales data, and during use, upon receipt from the input layer, maps the purchasing power data to the at least one variable based on the mapping of the prior purchasing power data to the sales data; and
an output layer to map the at least one variable to the value of the vehicle recommendation as a function of the internal layer;

determining, via use of the trained machine learning model, the vehicle recommendation based on the at least one mapped variable; and
transmitting, to the user device, a notification indicating the vehicle recommendation.

2. The computer-implemented method of claim 1 , wherein the transactional data further includes a debt, a loan, an additional income, or a credit score of the user.

3. The computer-implemented method of claim 1 , wherein the one or more transactional entities include one or more merchants including one or more vehicle dealers, financial services providers, or online resources.

4. The computer-implemented method of claim 3 , wherein the one or more transactional entities include the one or more vehicle dealers, and wherein the sales data of the one or more vehicles further includes one or more dealer identifications associated with the one or more vehicle dealers.

5. The computer-implemented method of claim 3 , wherein the one or more transactional entities include the one or more vehicle dealers, the computer-implemented method further including transmitting, to the one or more vehicle dealers, the notification indicating the vehicle recommendation.

6. The computer-implemented method of claim 1 , wherein the purchasing power data further includes demographic information of the user.

7. The computer-implemented method of claim 1 , wherein mapping the purchasing power data with the at least one variable includes comparing the vehicle price range of the user, the personalized monthly payment amount of the user, and the sale prices of the one or more vehicles.

8. The computer-implemented method of claim 1 , further including, prior to obtaining the transactional data of the user, authenticating a user identification of the user.

9. The computer-implemented method of claim 1 , further including, prior to training the machine learning model, determining, via the one or more processors, modified sales data of the one or more vehicles for the user based on the transactional data, the modified sales data including an actual personalized monthly payment amount for each of the one or more vehicles that is personalized for the user, such that the modified sales data for the one or more vehicles varies for other users.

10. The computer-implemented method of claim 9 , wherein the monthly payment goal includes the personalized monthly payment amount and a personalized annual percentage rate, and the modified sales data further includes an actual personalized annual percentage rate;
the method further including, prior to determining the vehicle recommendation, training the machine learning model, wherein:
the input layer receives the monthly payment goal and the modified sales data during training;
the internal layer, during training and upon receipt from the input layer, maps the monthly payment goal with the modified sales data, and during use, identifies the one or more vehicles having (i) the actual personalized annual percentage rate that matches the personalized annual percentage rate and (ii) the actual personalized monthly payment amount that matches the personalized monthly payment amount based on the mapping of the monthly payment goal to the modified sales data.

11. A computer system for providing a vehicle recommendation to a user, comprising:
a memory storing instructions; and
one or more processors configured to execute the instructions to perform operations including:
obtaining transactional data of the user and prior transactional data of a plurality of users from one or more transactional entities, wherein the transactional data comprises at least one of a salary or a spending pattern of the user;
determining purchasing power data of the user based on the transactional data and prior purchasing power data of the plurality of users based on the prior transactional data, wherein the purchasing power data comprises at least a vehicle price range;
obtaining sales data of one or more vehicles, wherein the sales data of the one or more vehicles comprises sale prices of the one or more vehicles;
training a machine learning model that includes a neural network of a plurality of layers to map one or more variables to a value of a vehicle recommendation, wherein the plurality of layers includes:
a first layer that receives the prior purchasing power data and the sales data during training, and the purchasing power data during use;
a second layer that, during training and upon receipt from the first layer, maps the prior purchasing power data to the sales data, and during use and upon receipt from the first layer, maps the purchasing power data to the one or more variables based on the mapping of the prior purchasing power data to the sales data;
a third layer that maps the one or more variables to the value of the vehicle recommendation as a function of the second layer;

determining the vehicle recommendation, using the trained machine learning model, based on the one or more mapped variables; and
transmitting, to the user, a notification indicating the vehicle recommendation.

12. The computer system of claim 11 , wherein the one or more processors are configured to execute the instructions to perform operations including:
prior to training the machine learning model, determining modified sales data of the one or more vehicles for the user based on the transactional data and the sales data, wherein the modified sales data includes at least an actual personalized monthly payment amount that is personalized to the user for each vehicle, such that the actual personalized monthly payment amount is different for a second user for each of the one or more vehicles.

13. The computer syste

Assignees

• Capital One Services Llc

Inventors

• Subramanian Ponnazhakan
• Unnikrishnan Sasi Kumar
• Chikkaveerappa Satish

Classifications

• G06Q30/0611

  Request for offers or quotes · CPC title

• G06Q30/0625

  by formulating product or service queries, e.g. using keywords or predefined options · CPC title

• G06Q30/0631 Primary

  Recommending goods or services · CPC title

• G06Q40/02

  Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03) · CPC title