E-COMMERCE RECOMMENDATIONS BASED ON SOCIAL EVENTS

• US 20200134692A1
• Filed: 10/26/2018
• Published: 04/30/2020
• Est. Priority Date: 10/26/2018
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: DELUCA, Lisa Seacat, ANDERS, Kelley, GREENBERGER, Jeremy A., FOX, Jeremy R.
• Application Number:
  US16/172,673
• Publication Number:
  US 20200134692A1
• Time in Patent Office: Days
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A recommendations engine at a server determines that a user at a client device is accessing a website. The recommendations engine retrieves data of the user from one or more social media platforms and analyzes the data of the user to identify social events of the user. The recommendations engine generates a set of product recommendations for the user based at least on the social events of the user and causes an output of the set of product recommendations on the website. In one aspect of the present invention, as the user continues to navigate the website, the process is repeated. As new social events of the user are identified, the product recommendations for the user are modified. In this manner, real-time social events of the user can be used to dynamically modify the product recommendations presented to the user.

Claims

1. A method for product recommendations on websites based on user social events, comprising:

determining, by a recommendations engine at a server, that a user at a client device is accessing a website;

retrieving, by the recommendations engine, data of the user from one or more social media platforms;

analyzing, by the recommendations engine, the data of the user to identify social events of the user;

generating, by the recommendations engine, a set of product recommendations for the user based at least on the social events of the user; and

causing, by the recommendations engine, an output of the set of product recommendations on the website.

2. The method of claim 1, wherein a given product recommendation of the set of product recommendations further comprise an indication of a reasoning behind the given product recommendation based on a given social event of the user, wherein the recommendations engine further causes an output of the indication with the given product recommendation on the website.

3. The method of claim 2, wherein the recommendations engine further causes a feedback mechanism to be output on the website to hide the given product recommendation or to show more product recommendations matching the given social event of the user.

4. The method of claim 1, wherein the generating of the set of product recommendations comprises:

determining, by the recommendations engine, one or more most popular social events of the user; and

generating, by the recommendations engine, the set of product recommendations for the user based at least on the one or more most popular social events of the user.

5. The method of claim 1, wherein the generating of the set of product recommendations comprise:

generating a cross co-occurrence matrix using a data file containing parameters describing behavior of the user, the data file comprising the social events of the user; and

generating the set of product recommendations using the cross co-occurrence matrix.

6. A computer program product for product recommendations on websites based on user social events, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

determine that a user at a client device is accessing a website;

retrieve data of the user from one or more social media platforms;

analyze the data of the user to identify social events of the user;

generate a set of product recommendations for the user based at least on the social events of the user; and

cause an output of the set of product recommendations on the website.

7. The computer program product of claim 6, wherein a given product recommendation of the set of product recommendations further comprise an indication of a reasoning behind the given product recommendation based on a given social event of the user, wherein the processor further causes an output of the indication with the given product recommendation on the website.

8. The computer program product of claim 7, wherein the processor further causes a feedback mechanism to be output on the website to hide the given product recommendation or to show more product recommendations matching the given social event of the user.

9. The computer program product of claim 6, wherein the generating of the set of product recommendations comprises:

determine one or more most popular social events of the user; and

generate the set of product recommendations for the user based at least on the one or more most popular social events of the user.

10. The computer program product of claim 6, wherein the generating of the set of product recommendations comprise:

generate a cross co-occurrence matrix using a data file containing parameters describing behavior of the user, the data file comprising the social events of the user; and

generate the set of product recommendations using the cross co-occurrence matrix.

11. A system comprising:

a processor; and

a computer readable storage medium having program instructions embodied therewith, the program instructions executable by the processor to cause the processor to;

determine that a user at a client device is accessing a website;

retrieve data of the user from one or more social media platforms;

analyze the data of the user to identify social events of the user;

generate a set of product recommendations for the user based at least on the social events of the user; and

cause an output of the set of product recommendations on the website.

12. The system of claim 11, wherein a given product recommendation of the set of product recommendations further comprise an indication of a reasoning behind the given product recommendation based on a given social event of the user, wherein the processor further causes an output of the indication with the given product recommendation on the website.

13. The system of claim 12, wherein the processor further causes a feedback mechanism to be output on the website to hide the given product recommendation or to show more product recommendations matching the given social event of the user.

14. The system of claim 11, wherein the generating of the set of product recommendations comprises:

determine one or more most popular social events of the user; and

generate the set of product recommendations for the user based at least on the one or more most popular social events of the user.

15. The system of claim 11, wherein the generating of the set of product recommendations comprise:

generate a cross co-occurrence matrix using a data file containing parameters describing behavior of the user, the data file comprising the social events of the user; and

generate the set of product recommendations using the cross co-occurrence matrix.