Peer-based selection using machine learning

Patent metadata

Field	Value
Publication number	US-12450641-B2
Application number	US-202217657250-A
Country	US
Kind code	B2
Filing date	Mar 30, 2022
Priority date	Mar 30, 2022
Publication date	Oct 21, 2025
Grant date	Oct 21, 2025

Abstract

In some implementations, a system may generate a first exchange profile for a first user and a second exchange profile for a second user. The first exchange profile may identify one or more characteristics of an exchange behavior of the first user based on exchange data of the first user, and the second exchange profile may identify one or more characteristics of an exchange behavior of the second user based on exchange data of the second user. The system may receive, from a first device of the first user, a request for a selection for the first user. The system may determine, based on the first exchange profile and the second exchange profile, an entity that is relevant to the first user. The system may transmit, to the first device of the first user, information indicating the selection for the first user, where the selection identifies the entity.

First claim

What is claimed is:

1. A system for peer-based selection using machine learning, the system comprising:
one or more memories; and
one or more processors, communicatively coupled to the one or more memories, configured to:
train a machine learning model using a feature set that includes a category of an exchange, an amount of an exchange, a location of an exchange, and a recency of an exchange,
wherein the feature set is associated with a target variable value that is associated with a value the machine learning model is trying to predict, and
wherein the machine learning model is trained to recognize patterns in the feature set that lead to the target variable value;

generate a first exchange profile for a first user and a second exchange profile for a second user,
wherein the first exchange profile identifies one or more characteristics of an exchange behavior of the first user based on exchange data of the first user, and the second exchange profile identifies one or more characteristics of an exchange behavior of the second user based on exchange data of the second user;

receive, from a first device of the first user and based on performing a near field communication (NFC) or Bluetooth Low Energy (BLE) interaction of the first device of the first user with a second device of the second user, a request for a selection for the first user that is based on the exchange behavior of the second user;
provide, to the machine learning model and based on receiving the request for the selection via the NFC or BLE interaction, first information indicating a category of a first exchange associated with the first exchange profile, an amount of the first exchange, a location of the first exchange, and a recency of the first exchange;
provide, to the machine learning model and based on receiving the request for the selection via the NFC or BLE interaction, second information indicating a category of a second exchange associated with the second exchange profile, an amount of the second exchange, a location of the second exchange, and a recency of the second exchange;
determine, based on processing the first information and the second information using the machine learning model, an entity involved in at least one exchange of the second user that is relevant to the first user,
wherein the machine learning model predicts a value indicating a likelihood of interest associated with the entity;

transmit, to the first device of the first user, information indicating the selection for the first user, wherein the selection identifies the entity; and
automatically cause, based on transmitting the information indicating the selection and in response to receiving the request for the selection for the first user that is based on the exchange behavior of the second user, the first device of the first user to generate a calendar entry associated with the entity using a calendar service remote to the first device of the first user.

2. The system of claim 1 , wherein the one or more processors are further configured to:
transmit, automatically and based on determining the entity, a request for a reservation for the first user with the entity.

3. The system of claim 1 , wherein the machine learning model determines the entity based on the feature set.

4. The system of claim 1 , wherein processing the first exchange profile and the second exchange profile includes determining an intersection of the first exchange profile and the second exchange profile,
wherein the intersection indicates at least one characteristic of the one or more characteristics of the exchange behavior of the first user that corresponds to at least one characteristic of the one or more characteristics of the exchange behavior of the second user.

5. The system of claim 1 , wherein the second exchange profile relates to an entity category selected for sharing by the second user.

6. The system of claim 1 , wherein the one or more characteristics of the exchange behavior of the first user or the one or more characteristics of the exchange behavior of the second user include one or more of volumes of exchanges for one or more entities, frequencies of exchanges for one or more entities, entity categories for one or more entities, or locations for one or more entities.

7. The system of claim 1 , wherein the one or more processors are further configured to:
determine a location of the first user based on one or more recent exchanges of the first user,
wherein the entity that is determined is associated with the location of the first user.

8. The system of claim 1 , wherein the one or more processors, to determine the entity involved in the at least one exchange of the second user that is relevant to the first user, are configured to:
classify the entity in a cluster, wherein entities associated with the cluster have a threshold degree of similarity, and
selectively, based on the cluster, perform an automated action associated with the entity.

9. A non-transitory computer-readable medium storing a set of instructions for peer-based selection using machine learning, the set of instructions comprising:
one or more instructions that, when executed by one or more processors of a machine learning system, cause the machine learning system to:
train a machine learning model using a feature set that includes a category of an exchange, an amount of an exchange, a location of an exchange, and a recency of an exchange,
wherein the feature set is associated with a target variable value that is associated with a value the machine learning model is trying to predict, and
wherein the machine learning model is trained to recognize patterns in the feature set that lead to the target variable value; and

one or more instructions that, when executed by one or more processors of a first device of a first user, cause the first device to:
perform a physical interaction with a second device of a second user,
wherein the physical interaction is for initiating a request for a selection for the first user that is based on exchange behavior of the second user;

transmit, to a server device, the request for the selection for the first user based on performing the physical interaction;
receive, from the server device, based on the physical interaction, and based on using the machine learning model, information indicating the selection for the first user,
wherein the selection identifies an entity involved in at least one exchange of the second user that is relevant to the first user based on a first exchange profile for the first user that identifies one or more characteristics of an exchange behavior of the first user, and a second exchange profile for the second user that identifies one or more characteristics of the exchange behavior of the second user,
wherein information identified by the selection is provided to the machine learning model, and
wherein the machine learning model predicts a value indicating a likelihood of interest associated with the entity; and

automatically generate, based on receiving the information indicating the selection and in response to receiving the request for the selection for the first user that is based on the exchange behavior of the second user, a calendar entry associated with the entity using a remote calendar service.

10. The non-transitory computer-readable medium of claim 9 , wherein the physical interaction is an exchange of information between the first device and the second device using near field communication.

11. The non-transitory computer-readable medium of claim 9 , wherein the physical interaction is an exchange of information between the first device and the second device via applications imple

Assignees

• Capital One Services Llc

Inventors

• Cuan Lukiih
• Cody Lea
• Atkins Phoebe

Classifications

• G06N20/00

  Machine learning · CPC title

• G06Q10/02

  Reservations, e.g. for tickets, services or events · CPC title

• G06Q30/0631 Primary

  Recommending goods or services · CPC title