Automated mechanisms to resolve explore-exploit dilemma with adaptive revival opportunities

Patent metadata

Field	Value
Publication number	US-11055742-B2
Application number	US-201916263856-A
Country	US
Kind code	B2
Filing date	Jan 31, 2019
Priority date	Jan 30, 2018
Publication date	Jul 6, 2021
Grant date	Jul 6, 2021

Abstract

A method including displaying content elements on one or more websites to users. This method can also include tracking impression response data comprising (a) a response of the user to the content element of the content elements displayed on the one or more websites and (b) a time of the response of the user. Additionally, the method can include receiving a request from a first user. The method can further include determining weightings of the content elements based on posterior distributions using the impression response data, as adjusted by a temporal decay factor based on the times of the impression response data for the content elements. The method additionally can include generating the webpage to comprise the selected content element. Other embodiments are disclosed.

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 configured to run on the one or more processors and perform:
displaying content elements on one or more websites to users;
for each impression of a content element of the content elements being displayed on the one or more websites to a user of the users, tracking respective impression response data comprising (a) a respective response of the user to the content element of the content elements displayed on the one or more websites and (b) a respective time of the respective response of the user;
receiving a request from a first user of the users to display a webpage of the one or more websites;
determining weightings of the content elements based on posterior distributions using the respective impression response data, as adjusted by a temporal decay factor based on the respective times of the respective impression response data for the content elements;
selecting a selected content element from among the content elements based on the weightings of the content elements; and
generating the webpage to comprise the selected content element.

2. The system of claim 1 , wherein determining the weightings of the content elements further comprises:
generating a respective random sample from a respective posterior distribution of the posterior distributions for each content element of the content elements, using the respective impression response data, as adjusted by the temporal decay factor based on the respective time of the respective impression response data for the each content element.

3. The system of claim 1 , wherein:
the respective impression response data tracks conversion rate of the content elements by the users.

4. The system of claim 1 , wherein selecting the selected content element comprises:
determining a maximum of the weightings of the content elements; and
selecting the selected content element from among the content elements such that a weighting of the selected content element is the maximum of the weightings of the content elements.

5. The system of claim 1 , wherein:
the temporal decay factor is adapted based on changes in the respective impression response data using a correlation computation.

6. The system of claim 5 , wherein:
the temporal decay factor is further adapted differently based on different content element classes of the content elements.

7. The system of claim 1 , wherein:
the respective times of the respective impression response data are tracked on a weekly basis; and
the temporal decay factor is applied to adjust the respective impression response data on a weekly basis when the weightings of the content elements are determined.

8. The system of claim 1 , wherein :
each of the users is assigned a respective classification;
the respective impression response data further comprises, for each impression of the content element, (a) the respective classification of the user of the users, and (b) a respective response of the user in each of two channels; and
the weightings are further determined based on the respective classification of the first user and respective responses of the users in each of the two channels in the respective impression response data.

9. The system of claim 1 , further comprises:
determining a respective performance of each content element of the content elements on one or more websites to users in combination with personalization content selection techniques to determine a respective probability of selecting the each content element of the content elements.

10. The system of claim 9 , further comprises:
determining a respective performance of each content element of the content elements on one or more websites to users in combination with both omnichannel content selection techniques and personalization content selection techniques to determine the respective probability of selecting the each content element 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:
displaying content elements on one or more websites to users;
for each impression of a content element of the content elements being displayed on the one or more websites to a user of the users, tracking respective impression response data comprising (a) a respective response of the user to the content element of the content elements displayed on the one or more websites and (b) a respective time of the respective response of the user;
receiving a request from a first user of the users to display a webpage of the one or more websites;
determining weightings of the content elements based on posterior distributions using the respective impression response data, as adjusted by a temporal decay factor based on the respective times of the respective impression response data for the content elements;
selecting a selected content element from among the content elements based on the weightings of the content elements; and
generating the webpage to comprise the selected content element.

12. The method of claim 11 , wherein determining the weightings of the content elements further comprises:
generating a respective random sample from a respective posterior distribution of the posterior distributions for each content element of the content elements, using the respective impression response data, as adjusted by the temporal decay factor based on the respective time of the respective impression response data for the each content element.

13. The method of claim 11 , wherein:
the respective impression response data tracks conversion rate of the content elements by the users.

14. The method of claim 11 , wherein selecting the selected content element comprises:
determining a maximum of the weightings of the content elements; and
selecting the selected content element from among the content elements such that a weighting of the selected content element is the maximum of the weightings of the content elements.

15. The method of claim 11 , wherein:
the temporal decay factor is adapted based on changes in the respective impression response data using a correlation computation.

16. The method of claim 15 , wherein:
the temporal decay factor is further adapted differently based on different content element classes of the content elements.

17. The method of claim 11 , wherein:
the respective times of the respective impression response data are tracked on a weekly basis; and
the temporal decay factor is applied to adjust the respective impression response data on a weekly basis when the weightings of the content elements are determined.

18. The method of claim 11 , wherein:
each of the users is assigned a respective channel classification;
the respective impression response data further comprises, for each impression of the content element, (a) the respective channel classification of the user of the users, and (b) a respective response of the user in each of two channels; and
the weightings are further determined based on the respective channel classification of the first user and respective responses of the users in each of the two channels in the respective impression response data.

19. The method of claim 11 , wherein:
the users are classified into respective segments;
the respective impression response data further comprises, for each impression of the

Assignees

• Walmart Apollo Llc

Inventors

• Mitra Abhimanyu
• Achan Kannan
• Kashyap Abhay
• Ali Afroza
• Deshpande Omkar

Classifications

• G06Q30/0246

  Traffic · CPC title

• G06Q30/0263 Primary

  based upon Internet or website rating · CPC title

• G06Q30/0277

  Online advertisement · CPC title