Utilizing a machine learning model to determine interests and recommendations for a customer of a merchant

Patent metadata

Field	Value
Publication number	US-2021012407-A1
Application number	US-201916506620-A
Country	US
Kind code	A1
Filing date	Jul 9, 2019
Priority date	Jul 9, 2019
Publication date	Jan 14, 2021
Grant date	—

Abstract

A device may receive third-party data associated with merchants and may receive customer interest data associated with customers of the merchants, wherein the customer interest data includes data identifying locations of the customers and birthdates of the customers. The device may train a machine learning model, with the third-party data and the customer interest data, to generate a trained machine learning model. The device may receive, from a user device, data identifying a location and a birthdate of a particular customer of a particular merchant, wherein the particular merchant is one of the merchants, and may process the data identifying the location and the birthdate of the particular customer, with the trained machine learning model, to determine a predicted interest of the particular customer. The device may perform one or more actions based on the interest of the particular customer.

First claim

1 . A method, comprising:
accessing, by a device, third-party data associated with merchants,
wherein the third-party data includes data associated with one or more products of the merchants;
accessing, by the device, customer interest data associated with customers of the merchants,
wherein the customer interest data includes first data identifying:
locations of the customers, and
birthdates of the customers;

training, by the device and with the third-party data and the customer interest data, a machine learning model, to generate a trained machine learning model,
the trained machine learning model to identify trends associated with a cluster of customers based on the locations of the customers, the birthdates of the customers,
and astrological data associated with the birthdates; receiving, by the device and from a user device, second data identifying a location and a birthdate of a particular customer; processing, by the device and with the trained machine learning model, the second data identifying the location and the birthdate of the particular customer to determine one or more products of the merchants that are predicted to match a profile of the particular customer; and performing, by the device, one or more actions based on the one or more products of the merchants that are predicted to match the profile of the particular customer,
the one or more actions including one or more of:
restricting use, by the user device, of a website associated with a particular merchant of the merchants;
or
retraining the machine learning model based on an interest of the particular customer.

2 . (canceled)

3 . The method of claim 1 , further comprising:
receiving third data identifying an input provided by the particular customer via the user device,
wherein the input is associated with the particular merchant;
processing the third data identifying the input provided by the particular customer, with the trained machine learning model, to determine another interest of the particular customer; and performing one or more additional actions based on the other interest of the particular customer.

4 . The method of claim 3 , wherein performing the one or more additional actions comprises one or more of:
providing, to the user device, fourth data identifying a recommendation for the particular customer and associated with the particular merchant; providing, to the user device, fifth data identifying an offer for the particular customer and associated with the particular merchant; restricting use, by the user device, of a website associated with the particular merchant; pre-approving the particular customer for a transaction with the particular merchant; or retraining the machine learning model based on the other interest of the particular customer.

5 . The method of claim 1 , wherein the customer interest data further includes one or more of:
social media data associated with the customers, transaction data associated with the customers, or website activity data associated with the customers.

6 . The method of claim 1 , further comprising:
receiving transaction data associated with a transaction between the particular customer and the particular merchant; processing the transaction data, with the trained machine learning model, to determine another interest of the particular customer; and performing one or more additional actions based on the other interest of the particular customer.

7 . The method of claim 6 , wherein the transaction data relates to one or more of:
a particular product offered by the particular merchant, or a particular service offered by the particular merchant.

8 . A device, comprising:
one or more memories; and one or more processors communicatively coupled to the one or more memories, configured to:
receive, from a user device, first data identifying a location and a birthdate of a particular customer,
process, with a trained machine learning model, the first data identifying the location and the birthdate of the particular customer to determine a predicted interest of the particular customer,
wherein the trained machine learning model is to identify trends associated with a cluster of customers based on the locations of the customers, the birthdates of the customers, and astrological data associated with the birthdates,
wherein the trained machine learning model is trained with data associated with merchants and customer interest data associated with customers of the merchants, to generate the trained machine learning model,
wherein the data associated with the merchants includes data associated with one or more products of the merchants, and
wherein the customer interest data includes second data identifying:
 locations of the customers, and
 birthdates of the customers; and

perform one or more actions based on the predicted interest of the particular customer,
wherein, when performing the one or more actions, the one or more processors are configured to one or more of:
restrict use, by the user device, of a website associated with a particular merchant of the merchants;
or
retrain the machine learning model based on an interest of the particular customer.

9 . The device of claim 8 , wherein the one or more processors are further configured to:
receive social media data associated with the particular customer; process the social media data, with the trained machine learning model, to determine another interest of the particular customer; and perform one or more additional actions based on the other interest of the particular customer.

10 . The device of claim 8 , wherein the one or more processors are further configured to:
receive website activity data associated with the particular customer; process the website activity data, with the trained machine learning model, to determine another interest of the particular customer; and perform one or more additional actions based on the other interest of the particular customer.

11 . The device of claim 8 , wherein the one or more processors are further configured to:
receive one or more of:
transaction data associated with a transaction between the particular customer and the particular merchant,
social media data associated with the particular customer, or
website activity data associated with the particular customer;
process the one or more of the transaction data, the social media data, or the website activity data, with the trained machine learning model, to determine a modification to the predicted interest of the particular customer; and perform one or more additional actions based on the modification to the predicted interest of the particular customer.

12 . The device of claim 8 , wherein the machine learning model includes one or more of:
a neural network classifier model, a long short-term memory (LSTM) model, or a reinforcement learning model.

13 . The device of claim 8 , wherein, when performing the one or more actions, the one or more processors are configured to:
provide, to the user device, third data identifying a recommendation for the particular customer and associated with the particular merchant; and the one or more processors are further configured to:
receive, from the user device, data indicating an interaction with the recommendation;
update the recommendation, to generate an updated recommendation, based on the data indicating the interaction with the recommendation; and
provide, to the user device, fourth data identifying the updated recommendation.

14 . The device of claim 8 , wherein, when performing the one or more ac

Assignees

• Capital One Services Llc

Inventors

• Kumar Lokesh Vijay
• Unnikrishnan Sasi Kumar
• Parcha Venkata Satya
• Chikkaveerappa Satish
• Subramanian Ponnazhakan

Classifications

• G06Q30/0621 Primary

  by configuring or customising goods or services · CPC title

• G06Q30/0631 Primary

  Recommending goods or services · CPC title

• G06F18/24

  Classification techniques · CPC title

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06N3/09

  Supervised learning · CPC title