Systems and methods for estimating click-through-rates of content items on a rendered page

• US 20060095281A1
• Filed: 11/30/2004
• Published: 05/04/2006
• Est. Priority Date: 10/29/2004
• Status: Active Grant

• Current Assignee: Zhigu Holdings Limited
• Original Assignee: Microsoft Corporation
• Inventors: Najm, Tarek, Li, Li, Chickering, David M., Meek, Christopher A., Li, Ying, Heckerman, David E., Prasad, Rajeev, Vajjiravel, Murali, Dhawan, Sachin, Burdick, Brian, Kagalwala, Raxit
• Granted Patent: US 7,983,959 B2
• Time in Patent Office: Days
• US Class Current: 705/37
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06Q 30/0247 Calculate past, present or future revenues
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 30/08 Auctions
• CPC Class Codes: G06Q 40/04 Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange

Abstract

Systems and methods for determining the value of bids placed by content providers for placement positions on a page, e.g., a web page, rendered according to a given context, for instance, the search results listing for a particular query initiated on a search engine web site, are provided. Additionally, systems and methods are provided for determining placement of content items, e.g., advertisements and/or images, on a rendered page relative to other content items on the page based upon bid value.

Claims

1. A computer-implemented method for estimating a click-through-rate for at least one content item to be placed on a rendered page, the content item having a plurality of available content item types and the page having plurality of available content item placement positions, the computer-implemented method comprising:

determining a reference context associated with a combination including a particular content item placement position and a particular content item type;

collecting performance data for the reference context;

determining a click-through-rate for the reference context based on the performance data collected;

determining a click-through-rate for at least one additional context on the page relative to the click-through-rate for the reference context, the at least one additional context being associated with a different combination than the reference context;

collecting performance data for the at least one additional context;

determining an actual number of impressions of a particular content item in the additional context based on the performance data collected;

normalizing the actual number of impressions of the particular content item to any context on the rendered page; and

determining a click-through-rate estimate for the particular content item in any context on the rendered page.

2. The computer-implemented method of claim 1, wherein determining the actual number of impressions of the particular content item in the additional context comprises:

determining an actual number of impressions of the particular content item in the additional context that are clicked through based on the performance data collected; and

determining an actual number of impressions of the particular content item in the additional context that are not clicked through based on the performance data collected.

3. The computer-implemented method of claim 2, wherein normalizing the number of impressions of the particular content item to any context on the rendered page comprises:

normalizing the actual number of impressions of the particular content item that are clicked through to any context on the rendered page; and

normalizing the actual number of impressions of the particular content item that are not clicked through to any context on the rendered page.

4. The computer-implemented method of claim 1, further comprising receiving a plurality of bids each associated with a content item, at least one of the plurality of bids being based on a cost-per-click pricing model.

5. The computer-implemented method of claim 4, wherein receiving a plurality of bids comprises receiving at least one of the plurality of bids through an auction.

6. The computer-implemented method of claim 4, further comprising determining whether any of the plurality of bids received are to be targeted based upon at least one combination of one or more targeting attributes.

7. The computer-implemented method of claim 6, wherein if none of the plurality of bids received are to be targeted, determining the click-through-rate estimate for the particular content item in any context on the rendered page comprises determining a single click-through-rate for the particular content item.

8. The computer-implemented method of claim 6, wherein if any of the plurality of bids received are to be targeted, the method further comprises determining a click-through-rate for the particular content item according to each combination of one or more targeting attributes upon which any of the plurality of bids received are to be targeted.

9. The computer-implemented method of claim 8, wherein determining the click-through-rate for the particular content item according to each combination of one or more targeting attributes upon which any of the plurality of bids received are to be targeted comprises determining a targeted click-through-rate estimate for the particular content item in accordance with each combination of one or more targeting attributes.

10. A computer programmed to perform the steps recited in claim 1.

11. A computer-readable medium having computer-executable instructions embodied thereon for presenting a user interface on a display device, the user interface for estimating a click-through-rate for at least one content item to be placed on a rendered page, the content item having a plurality of available content item types and the page having a plurality of available content item placement positions, the computer-readable medium comprising:

code for determining a reference context associated with a combination including a particular content item placement position and a particular content item type;

code for collecting performance data for the reference context;

code for determining a click-through-rate for the reference context based on the performance data collected;

code for determining a click-through-rate for at least one additional context on the page relative to the click-through-rate for the reference context, the at least one additional context being associated with a different combination than the reference context;

code for collecting performance data for the at least one additional context;

code for determining an actual number of impressions of a particular content item in the additional context based on the performance data collected;

code for normalizing the actual number of impressions of the particular content item to any context on the rendered page; and

code for determining a click-through-rate estimate for the particular content item in any context on the rendered page.

12. The computer-readable medium of claim 11, wherein the code for determining the actual number of impressions of eth particular content item in the additional context is capable of determining an actual number of impressions of the particular content item in the additional context that are clicked through and determining an actual number of impressions of the particular content item in the additional context that are not clicked through based on the performance data collected.

13. The computer-readable medium of claim 12, wherein the code for normalizing the number of impressions of the particular content item to any context on the rendered page is capable of normalizing the actual number of impressions of the particular content item that are clicked through and normalizing the actual number of impressions of the particular content item that are not clicked through to any context on the rendered page.

14. The computer-readable medium of claim 11, further comprising code for receiving a plurality of bids each associated with a content item, at least one of the plurality of bids being based on a cost-per-click pricing model.

15. The computer-readable medium of claim 14, wherein the code for receiving a plurality of bids is cable of receiving at least one of the plurality of bids through an auction.

16. The computer-readable medium of claim 14, further comprising code for determining whether any of the plurality of bids received are to be targeted based upon at least one combination of one or more targeting attributes.

17. The computer-readable medium of claim 16, wherein if none of the plurality of bids are to be targeted, the code for determining a click-through-rate estimate for the particular content item in any context on the rendered page is capable of determining a single click-through-rate for the particular content item.

18. The computer-readable medium of claim 16, wherein if any of the plurality of bids received are to be targeted, the computer-readable medium further comprises code for determining a click-through-rate for the particular content item according to each combination of one or more targeting attributes upon which any of the plurality of bids received are to be targeted.

19. The computer-readable medium of claim 18, wherein the code for determining the click-through-rate for the particular content item according to each combination of one or more targeting attributes upon which any of the plurality of bids received are to be targeted is capable of determining a targeted click-through-rate estimate for the particular content item in accordance with each combination of one or more targeting attributes.

20. A computer-implemented method for estimating a relative content item placement position of a particular content item on a page rendered according to a given context based upon a proposed bid, comprising:

receiving a base bid associated with the particular content item;

determining if targeting of the base bid based upon one or more targeting attributes is desired;

if it is determined that targeting of the base bid is not desired, determining a bid value for the base bid; and

determining a position estimate based on the bid value determined.

21. The computer-implemented method of claim 20, wherein receiving a base bid associated with the particular content item comprises receiving the base bid through an auction.

22. The computer-implemented method of claim 20, wherein the given context is determined based upon a search query.

23. The computer-implemented method of claim 20, further comprising displaying the position estimate on a display device.

24. The computer-implemented method of claim 20, wherein if it is determined that targeting of the base bid is desired, the method further comprises:

receiving an indication of one or more desired targeting attributes;

receiving an indication of a bid adjustment to be associated with each of the one or more desired targeting attributes; and

determining a bid value for the targeted bid.

25. The computer-implemented method of claim 24, further comprising displaying the position estimate on a display device.

26. A computer-implemented method for estimating a bid value a content provider would have to bid to have a content item placed in a particular content item placement position on a page rendered according to a given context, comprising:

receiving an indication of the particular content item placement position;

determining if targeting based upon one or more targeting attributes is desired;

if it is determined that targeting bid is not desired, determining an estimated bid value the content provider would have to bid to have the content item placed in the particular content item placement position on the rendered page.

27. The computer-implemented method of claim 26, further comprising displaying the estimated bid value on a display device.

28. The computer-implemented method of claim 27, further comprising receiving an indication of a desired frequency for which the content provider desires to have the content item displayed in the particular content item placement position.

29. The computer-implemented method of claim 28, wherein if it is determined that targeting is not desired, determining the estimated bid value the content provider would have to bid to have the content item placed in the particular content item placement position comprises determining the estimated bid value the content provider would have to place in accordance with the desired frequency received.

30. The computer-implemented method of claim 26, wherein if it is determined that targeting is desired, the method further comprises:

receiving an indication of one or more desired targeting attributes; and

determining an estimated targeted bid value the content provider would have to bid to have the content item placed in the particular content item placement position on the rendered page.

31. The computer-implemented method of claim 30, further comprising displaying the estimated bid value on a display device.

32. The computer-implemented method of claim 31, further comprising receiving an indication of a desired frequency for which the content provider desires to have the content item displayed in the particular content item placement position.

33. The computer-implemented method of claim 32, wherein determining the estimated targeted bid value the content provider would have to bid to have the content item placed in the particular content item placement position on the rendered page comprises determining the estimated targeted bid value the content provider would have to bid in accordance with the desired frequency received.

34. A computer-readable medium having computer-executable instructions embodied thereon for presenting a user interface on a display device, the user interface for estimating a relative content item placement position of a particular content item on a page rendered according to a given context based upon a proposed bid, comprising:

code for receiving a base bid associated with the particular content item;

code for determining if targeting of the base bid based upon one or more targeting attributes is desired;

if it is determined that targeting of the base bid is not desired, code for determining a bid value for the base bid; and

code for determining a position estimate based on the bid value determined.

35. The computer-readable medium of claim 34, further comprising code for displaying the position estimate on a display device.

36. The computer-readable medium of claim 34, wherein if is determined that targeting of the base bid is desired, the computer-readable medium further comprises:

code for receiving an indication of one or more desired targeting attributes;

code for receiving an indication of a bid adjustment to be associated with each of the one or more desired targeting attributes; and

code for determining a bid value for the targeted bid.

37. A computer-readable medium having computer-executable instructions embodied thereon for presenting a user interface on a display device, the user interface for estimating a bid value a content provider would have to bid to have a content item placed in a particular content item placement position on a page rendered according to a given context comprising:

code for receiving an indication of the particular content item placement position;

code for determining if targeting based upon one or more targeting attributes is desired; and

if it is determined that targeting is not desired, code for determining an estimated bid value the content provider would have to bid to have the content item placed in the particular content item placement position on the rendered page.

38. The computer-readable medium of claim 37, further comprising code for displaying the estimated bid value on a display device.

39. The computer-readable medium of claim 37, further comprising code for receiving an indication of a desired frequency for which the content provider desires to have the content item displayed in the particular content item placement position.

40. The computer-readable medium of claim 37, wherein if it is determined that targeting is desired, the computer-readable medium further comprises:

code for receiving an indication of one or more desired targeting attributes; and

code for determining an estimated targeted bid value the content provider would have to bid to have the content item placed in the particular content item placement position on the rendered page.