Automatic resolution of the explore-exploit decision in omnichannel settings

Patent metadata

Field	Value
Publication number	US-12033178-B2
Application number	US-202318142834-A
Country	US
Kind code	B2
Filing date	May 3, 2023
Priority date	Jan 30, 2018
Publication date	Jul 9, 2024
Grant date	Jul 9, 2024

Abstract

A method including tracking impression response data in response to online impressions of content elements displayed to users of a website. The method also can include performing a classification of the users based on the impression response data. The method additionally can include generating a webpage of the website to comprise a content element selected from among the content elements based on the classification of a user of the users. Other embodiments are described.

First claim

What is claimed is:

1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computing instructions that, when executed by the one or more processors, cause the one or more processors to perform:
tracking impression response data in response to online impressions of content elements displayed to users of a website;
performing a classification of the users based on the impression response data; and
generating a webpage of the website to comprise a content element selected from among the content elements based on the classification of a user of the users.

2. The system of claim 1 , wherein:
the classification of the user is either a first group or a second group;
the user is classified into the first group when: (a) a quantity of conversions using a first channel for the user is greater than or equal to a first threshold during a first time period, and (b) a quantity of conversions using a second channel for the user is less than a second threshold during the first time period; and
the user is classified into the second group when the quantity of the conversions using the second channel for the user is greater than or equal to the second threshold during the first time period.

3. The system of claim 2 , wherein:
the first channel is one or more physical stores associated with the website; and
the second channel is the website.

4. The system of claim 2 , wherein:
the first threshold is one.

5. The system of claim 2 , wherein:
the second threshold is one.

6. The system of claim 2 , wherein:
the first time period is approximately three months.

7. The system of claim 1 , wherein:
each of the content elements comprises information regarding one or more items available on a second channel.

8. The system of claim 1 , wherein tracking impression response data comprises:
tracking first responses based on whether or not the users performed a first channel conversion associated with the content elements, wherein the first channel conversion is performed when a respective user of the users purchased at least one item displayed in a respective content element of the content elements in a first channel within a second time period of the respective content element being displayed on a second channel to the respective user; and
tracking second responses based on whether or not the users performed a second channel conversion associated with the content elements; wherein the second channel conversion is performed when the respective user purchased at least one item displayed in the respective content element in the second channel within a third time period of the respective content element being displayed on the second channel to the respective user.

9. The system of claim 8 , wherein:
the second time period is approximately seven days; and
the third time period is approximately seven days.

10. The system of claim 1 , wherein generating the webpage to comprise the content element selected from among the content elements comprises:
for each respective content element of the content elements:
generating a first posterior distribution for a first channel conversion being performed for the respective content element by users in the classification of the user, based on the impression response data for the respective content element;
generating a first random sample from the first posterior distribution;
generating a second posterior distribution for a second channel conversion being performed for the respective content element by users in the classification of the user, based on the impression response data for the respective content element;
generating a second random sample from the second posterior distribution;
selecting a maximum of the first random sample and the second random sample; and
determining a weighting for the respective content element based on the maximum of the first random sample and the second random sample; and

selecting the content element from among the content elements such that the weighting of the content element is a maximum of the weightings of the content elements.

11. A method being implemented via execution of computing instructions configured to run at one or more processors and stored at one or more non-transitory computer-readable media, the method comprising:
tracking impression response data in response to online impressions of content elements displayed to users of a website;
performing a classification of the users based on the impression response data; and
generating a webpage of the website to comprise a content element selected from among the content elements based on the classification of a user of the users.

12. The method of claim 11 , wherein:
the classification of the user is either a first group or a second group;
the user is classified into the first group when: (a) a quantity of conversions using a first channel for the user is greater than or equal to a first threshold during a first time period, and (b) a quantity of conversions using a second channel for the user is less than a second threshold during the first time period; and
the user is classified into the second group when the quantity of the conversions using the second channel for the user is greater than or equal to the second threshold during the first time period.

13. The method of claim 12 , wherein:
the first channel is one or more physical stores associated with the website; and
the second channel is the website.

14. The method of claim 12 , wherein:
the first threshold is one.

15. The method of claim 12 , wherein:
the second threshold is one.

16. The method of claim 12 , wherein:
the first time period is approximately three months.

17. The method of claim 11 , wherein:
each of the content elements comprises information regarding one or more items available on a second channel.

18. The method of claim 11 , wherein tracking impression response data comprises:
tracking first responses based on whether or not the users performed a first channel conversion associated with the content elements, wherein the first channel conversion is performed when a respective user of the users purchased at least one item displayed in a respective content element of the content elements in a first channel within a second time period of the respective content element being displayed on a second channel to the respective user; and
tracking second responses based on whether or not the users performed a second channel conversion associated with the content elements; wherein the second channel conversion is performed when the respective user purchased at least one item displayed in the respective content element in the second channel within a third time period of the respective content element being displayed on the second channel to the respective user.

19. The method of claim 18 , wherein:
the second time period is approximately seven days; and
the third time period is approximately seven days.

20. The method of claim 11 , wherein generating the webpage to comprise the content element selected from among the content elements comprises:
for each respective content element of the content elements:
generating a first posterior distribution for a first channel conversion being performed for the respective content element by users in the classification of the user, based on the impression response data for the respective content element;
generating a first random sample from the first posterior distribution;
generating a

Assignees

• Walmart Apollo Llc

Inventors

• Mitra Abhimanyu
• Subramaniam Sinduja
• Korpeoglu Evren
• Achan Kannan

Classifications

• H04L67/535

  Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34) · CPC title

• H04L67/02

  based on web technology, e.g. hypertext transfer protocol [HTTP] · CPC title

• G06F16/285

  Clustering or classification · CPC title

• G06Q30/0242 Primary

  Determining effectiveness of advertisements · CPC title