Methods and systems for deriving a score with which item listings are ordered when presented in search results

• US 8,903,816 B2
• Filed: 06/01/2009
• Issued: 12/02/2014
• Est. Priority Date: 04/08/2009
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Dumon, Olivier G., McDonald, Ryan, Rehman, Muhammad Faisal, Netzloff, Julie, Sun, Ken
• Primary Examiner(s): Wu, Yicun
• Application Number:
  US12/476,046
• Publication Number:
  US 20100262602A1
• Time in Patent Office: 2,010 Days
• Field of Search: 707/706, 707/707
• US Class Current: 707/728
• CPC Class Codes: G06F 16/90335 Query processing
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0603 Catalogue ordering
• CPC Class Codes: G06Q 30/0623 Item investigation
• CPC Class Codes: G06Q 30/0629 for generating comparisons
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

Methods and systems for analyzing, ordering and presenting item listings are described. In one example embodiment, a search query is processed to identify item listings satisfying the search query. Then, for each item listing that satisfies the search query, a ranking score is derived and assigned to the item listing. The ranking score is based in part on a relevance score, a listing quality score and a business rules score (or, adjustment factor). Finally, the item listings are ordered, based on their corresponding ranking score, and presented in order in a search results page.

Claims

1. A computer-implemented method comprising:

processing a query to identify item listings that satisfy the query, each item listing comprising data representing one or more attributes of a product or service offered for sale;

assigning a ranking score to each item listing that satisfies the query, the ranking score derived as the product of two or more component scores including a first component score representing a measure of relevance between search terms in a search query and the item listing, the second component score being independent of the query and representing a measure of quality for the item listing, the measure of quality being based at least in part on at least one of (i) an attribute of the item listing determinable at a time of listing, or (ii) an observed sales performance of the item listing or an item listing similar thereto; and

presenting the item listings that satisfy the query in a search results page, the item listings positioned in the search results page based on the ranking score assigned to each item listing.

2. The computer-implemented method of claim 1, wherein presenting the item listings positioned in the search results page based on the ranking score assigned to each item listing includes generating a list of the item listings ordered based on the ranking score assigned to each item listing such that the item listing assigned the highest ranking score is first in the list and the item listing assigned the lowest ranking score is last in the list.

3. The computer-implemented method of claim 1, wherein the second component score representing a measure of quality for the item listing is calculated as a probability that an item listing will conclude a transaction if displayed in a search results page, the probability derived based on an analysis of historical data for item listings determined to be similar.

4. The computer-implemented method of claim 1, wherein the second component score representing a measure of quality for the item listing is calculated as a probability that an item listing will conclude a transaction if displayed in a search results page, the probability derived based on an observed demand metric.

5. The computer-implemented method of claim 4, wherein the observed demand metric is the number of transactions concluded per the number of search impressions for the item listing.

6. The computer-implemented method of claim 3, wherein item listings determined to be similar are item listings in the same category as the item listing to which the ranking score is being assigned.

7. The computer-implemented method of claim 1, wherein the second component score representing a measure of quality for the item listing is calculated as a probability that the item listing will conclude a transaction if displayed in a search results page, the probability derived based on an analysis of an observed demand metric representing a measure of performance for the item listing.

8. The computer-implemented method of claim 7, wherein the measure of performance for the item listing is derived by determining the ratio of transactions concluded per the number of search impressions for the item listing.

9. The computer-implemented method of claim 1, wherein the second component score representing a measure of quality for the item listing is calculated as a probability that an item listing will conclude a transaction if displayed in a search results page, the probability derived based on an analysis of observed metrics representing a measure of performance for item listings determined to be similar.

10. The computer-implemented method of claim 1, further comprising:

adjusting, with an intermingler module, an order of item listings to ensure that a target ratio of item listings in different categories is presented in the search results page.

11. The computer-implemented method of claim 1, wherein, in addition to the first and second component scores, the ranking score is derived as the product of a third component score representing a business rules score, the business rules score i) derived by evaluating one or more business rules, and ii) resulting in a promotion or demotion of an item listing.

12. The computer-implemented method of claim 11, wherein the promotion or demotion of the item listing represents a change in the position of the item listing in the search results page as a result of multiplying the ranking score of the item listing by the business rules score for the item listing.

13. A system comprising:

a processor-implemented search engine module configured to process a query to identify item listings that satisfy the query, each item listing comprising data representing one or more attributes of a product or service offered for sale;

a processor-implemented ranking score assignment module configured to assign a ranking score to each item listing that satisfies the query, the ranking score derived as the product of two or more component scores including a first component score representing a measure of relevance between search terms in the query and the item listing, the second component score being independent of the query and representing a measure of quality for the item listing, the measure of quality being based at least in part on at least one of (i) an attribute of the item listing determinable at a time of listing, or (ii) an observed sales performance of the item listing or an item listing similar thereto; and

a processor-implemented presentation module to present the item listings that satisfy the query in a search results page, the item listings positioned in the search results page based on the ranking score assigned to each item listing.

14. The system of claim 13, wherein presenting the item listings positioned in the search results page based on the ranking score assigned to each item listing includes generating a list of the item listings ordered based on the ranking score assigned to each item listing such that the item listing assigned the highest ranking score is first in the list and the item listing assigned the lowest ranking score is last in the list.

15. The system of claim 13, wherein the second component score representing a measure of quality for the item listing is calculated as a probability that an item listing will conclude a transaction if displayed in a search results page, the probability derived based on an analysis of historical data for item listings determined to be similar.

16. The system of claim 13, wherein the second component score representing a measure of quality for the item listing is calculated as a probability that an item listing will conclude a transaction if displayed in a search results page, the probability derived based on an observed demand metric.

17. The system of claim 16, wherein the observed demand metric is the number of transactions concluded per the number of search impressions for the item listing.

18. The system of claim 15, wherein item listings determined to be similar are item listings in the same category as the item listing to which the ranking score is being assigned.

19. The system of claim 13, wherein the second component score representing a measure of quality for the item listing is calculated as a probability that the item listing will conclude a transaction if displayed in a search results page, the probability derived based on an analysis of observed metrics representing a measure of performance for the item listing.

20. The system of claim 19, wherein the measure of performance for the item listing is derived by determining the ratio of transactions concluded per the number of search impressions for the item listing.

21. The system of claim 13, wherein the second component score representing a measure of quality for the item listing is calculated as a probability that an item listing will conclude a transaction if displayed in a search results page, the probability derived based on an analysis of observed metrics representing a measure of performance for item listings determined to be similar.

22. The system of claim 13, further comprising:

an intermingler module to adjust an order of item listings to ensure that a target ratio of item listings in different categories is presented in the search results page.

23. The system of claim 13, wherein, in addition to the first and second component scores, the ranking score is derived as the product of a third component score representing a business rules score, the business rules score i) derived by evaluating one or more business rules, and ii) resulting in a promotion or demotion of an item listing.

24. The system of claim 23, wherein the promotion or demotion of the item listing represents a change in the position of the item listing in the search results page as a result of multiplying the ranking score of the item listing by the business rules score for the item listing.

25. A method comprising:

presenting item listings that satisfy a search query in a search results page, each item listing comprising data representing one or more attributes of a product or service offered for sale, the item listings ordered based on a ranking score assigned to each item listing, the ranking score derived as the product of three component scores including a first component score representing a measure of relevance between search terms in a search request and the individual item listings satisfying the search query, a second component score being independent of the search query and representing a measure of likelihood that presentation of the item listing in a search results page results in conclusion of a sale the measure of likelihood being based on a comparison of at least one item attribute of the item listings with at least one item attribute of item listings determined to be similar and for which historical data is available for predicting sales performance, the third component score representing an adjustment factor determined based on evaluation of one or more business rules.