APPLICATION RECOMMENDATION ENGINE

• US 20100250337A1
• Filed: 03/31/2009
• Published: 09/30/2010
• Est. Priority Date: 03/31/2009
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Kassaei, Farhang
• Granted Patent: US 10,984,397 B2
• Time in Patent Office: Days
• US Class Current: 705/10
• CPC Class Codes: G06Q 20/108 Remote banking, e.g. home banking
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0277 Online advertisement
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 30/08 Auctions

Abstract

A computed-implemented method and system for recommending business applications on a network-based marketplace are described. A user'"'"'s listings, representing items for sale on the marketplace, are harvested to calculate segmentation data and metrics that form a user profile. The user profile is compared with other similar users who have subscribed to various applications, and the impact those applications have had on the metrics of the similar users is calculated in order to determine what impact the applications will have on the user in question. The impact, combined with user preferences, is used to suggest appropriate applications, which are displayed to the user within the marketplace. If the user selects one of the applications, the application is added to the user'"'"'s profile and relevant listings are updated with the new application.

Claims

1. A computer-implemented system to recommend applications, the system comprising:

a profile module to create a user sales profile by calculating a plurality of metrics from a plurality of listings related to a user, the plurality of listings representing sale items on a network-based marketplace;

an impact module to assess an impact on the plurality of metrics by at least a portion of a plurality of applications;

a recommendation module to suggest at least one recommended application from the plurality of applications based on the impact; and

an update module to update a portion of the plurality of listings using the at least one recommended application.

2. The system of claim 1, wherein the impact module comprises:

a profile comparison module to compare sales profiles of sellers who have used the first application to the user sales profile to obtain a plurality of sellers with the sales profiles similar to the user;

a calculation module to calculate a prior metric for a first set of listings, the first set of listings related to a first seller of the plurality of sellers prior to use of the first application, the calculation module further operable to calculate an updated metric for a second set of listings, the second set of listings related to the first seller during the use of the first application; and

a listing comparison module to compare the updated metric to the prior metric to assess the impact.

3. The system of claim 1, wherein the user sales profile includes user sales data, the user sales data including listing categories, listing keywords, application subscriptions, and a volume of sales.

4. The system of claim 1, wherein the plurality of metrics comprises at least one of profit margins, an average selling price, Detailed Seller Ratings (DSRs) and feedback, inventory turnover rate, accuracy of listings, communication with customers, average time to delivery, or shipping charges.

5. The system of claim 1, wherein the plurality of applications are business applications designed to improve effectiveness of selling items on a network-based trading environment.

6. The system of claim 1, wherein the recommendation module is further operable to suggest at least one of the plurality of applications based on a recommendation score.

7. The system of claim 6, wherein the recommendation module calculates the recommendation score with a recommendation function using the impact, an application explicit rating, an application implicit rating, and an editor rating.

8. The system of claim 1, wherein the recommendation module is further operable to recommend the at least one of the plurality of applications based on user preferences.

9. The system of claim 1, wherein the recommendation module is further operable to rank the at least one of the plurality of applications in order of impact and user preferences.

10. A computed-implemented method to recommend applications, the method comprising:

creating a user sales profile by calculating a plurality of metrics from a plurality of listings related to a user, the plurality of listings representing sale items on a network-based marketplace;

assessing an impact on the plurality of metrics by at least a portion of a plurality of applications;

suggesting at least one recommended application from the plurality of applications based on the impact;

communicating to the user the at least one recommended application on a display device; and

updating a portion of the plurality of listings using the at least one recommended application.

11. The method of claim 10, wherein assessing the impact on a first metric of the plurality of metrics by a first application of the plurality of applications comprises:

comparing sales profiles of sellers who have used the first application to the user sales profile to obtain a plurality of sellers with the sales profiles similar to the user, the plurality of listings representing sale items on a network-based marketplace;

calculating a prior metric for a first set of listings, the first set of listings related to a first seller of the plurality of sellers prior to use of the first application;

calculating an updated metric for a second set of listings, the second set of listings related to the first seller during the use of the first application; and

comparing the updated metric to the prior metric to assess the impact.

12. The method of claim 10, wherein the user sales profile includes user sales data, the user sales data including listing categories, listing keywords, application subscriptions, and a volume of sales.

13. The method of claim 10, wherein the plurality of metrics comprises at least one of profit margins, an average selling price, Detailed Seller Ratings (DSRs) and feedback, inventory turnover rate, accuracy of listings, communication with customers, average time to delivery, or shipping charges.

14. The method of claim 10, wherein the plurality of applications are business applications designed to improve effectiveness of selling items on a network-based trading environment.

15. The method of claim 10, further comprising recommending at least one of the plurality of applications based on a recommendation score.

16. The method of claim 15, wherein the recommendation score is calculated by a recommendation function using the impact, an application explicit rating, an application implicit rating, and an editor rating.

17. The method of claim 10, wherein recommending the at least one of the plurality of applications is also based on user preferences.

18. The method of claim 10, further comprising ranking the at least one of the plurality of applications in order of impact and user preferences.

19. A system to recommend applications, the system comprising:

first means for creating a user sales profile by calculating a plurality of metrics from a plurality of listings related to a user, the plurality of listings representing sale items on a network-based marketplace;

second means for assessing an impact on the plurality of metrics by at least a portion of a plurality of applications; and

third means to recommend at least one of the plurality of applications based on the impact.

20. A machine-readable medium embodying instructions which, when executed by a machine, cause the machine to execute a method comprising:

creating a user sales profile by calculating a plurality of metrics from a plurality of listings related to a user, the plurality of listings representing sale items on a network-based marketplace;

assessing an impact on the plurality of metrics by at least a portion of a plurality of applications; and

recommending at least one of the plurality of applications based on the impact.

21. The machine-readable medium of claim 20, wherein assessing the impact on a first metric of the plurality of metrics for a first application of the plurality of applications comprises:

comparing sales profiles of sellers who have used the first application to the user sales profile to obtain a plurality of sellers with the sales profiles similar to the user;

calculating a prior metric for a first set of listings, the first set of listings related to a first seller of the plurality of sellers prior to use of the first application;

calculating an updated metric for a second set of listings, the second set of listings related to the first seller during the use of the first application; and

comparing the updated metric to the prior metric to assess the impact.