System and method for optimizing paid search advertising campaigns based on natural search traffic

• US 8,396,742 B1
• Filed: 12/05/2008
• Issued: 03/12/2013
• Est. Priority Date: 12/05/2008
• Status: Active Grant

• Current Assignee: Riosoft Holdings, Inc.
• Original Assignee: Covario, Inc. (Dentsu Group, Inc.)
• Inventors: Blume, Matthias, Zlotin, Dema, Mann, Russ, Navarro-Cantu, Raul, Macdonald, Craig
• Primary Examiner(s): Weiss, John
• Assistant Examiner(s): CAO, VINCENT M
• Application Number:
  US12/329,391
• Time in Patent Office: 1,558 Days
• Field of Search: 705/14
• US Class Current: 705/14.1
• CPC Class Codes: G06Q 30/0246 Traffic
• CPC Class Codes: G06Q 30/0256 User search

Abstract

The invention is a computer-implementable methodology for quantitatively assessing the impact of paid search advertising on the total visits (paid and organic search-based visits) from search engines and utilizing this assessment to improve search engine marketing performance. The methodology relies on the computation of a synergy score for each search engine keyword of interest or coefficients in a synergy equation. Once computed, the score can be used to repeatedly compute the total return on advertising spend (ROAS) and other performance metrics on a go-forward basis without the time lag inherent in computing the synergy score itself. The invention includes specific computer-implementable methods for improving search engine marketing performance based on the total (paid plus organic) performance metrics.

Claims

1. A computer implemented method for determining an impact of a change to a paid portion of a search advertising campaign that is associated with a website, comprising:

identifying a first change made by an advertiser to the paid portion of the search advertising campaign, the first change affecting a cost of the paid portion;

determining, with a first computing device, one or more effects of the first change, the one or more effects being indicative of;

a change in a volume of search traffic resulting from the paid portion, and

a change in a volume of search traffic resulting from an unpaid portion of the search advertising campaign;

processing, with the first computing device or a second computing device, the one or more determined effects to generate a first synergy score, wherein the first synergy score quantifies an impact of the first change on the volume of search traffic resulting from the unpaid portion; and

storing the first synergy score in a machine readable memory in association with an indication of the first change.

2. The method of claim 1, wherein the first change includes a change selected from the group consisting of a start of advertising for at least a first keyword, a stoppage of advertising for at least a second keyword, a change to a maximum cost-per-click bid for at least a third keyword, a change to a budget limit for at least a fourth keyword and a change to a time period during which an advertisement is shown in relation to at least a fifth keyword.

3. The method of claim 1, where the one or more determined effects further include one or more effects selected from the group consisting of:

one or more changes to one or more volumes of traffic from one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines,

one or more changes to one or more click-through-rates associated with one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines,

one or more changes to one or more volumes of orders associated with one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines,

one or more changes to revenue associated with one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines,

one or more changes to one or more number of page views associated with one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines, and

one or more changes to one or more whitepaper downloads associated with one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines.

4. The method of claim 3, wherein the processing the one or more determined effects includes comparing a difference between a volume of traffic from an organic listing of the website at a search engine during a time period existing before the first change and a volume of traffic from an organic listing of the website at the search engine during a time period existing after the first change to a difference between a volume of traffic from a paid search listing of the website at the search engine during the time period existing before the first change and a volume of traffic from a paid search listing of the website at the search engine during the time period existing after the first change.

5. The method of claim 3, wherein the processing the one or more determined effects includes plotting, over a period of time, a relationship between a plurality of the one or more changes to the one or more click-through-rates associated with the one or more organic listings of the website at the one or more search engines and a corresponding plurality of the one or more changes to the one or more click-through-rates associated with the one or more paid search listings of the website at the one or more search engines.

6. The method of claim 1, further comprising:

generating a mathematical model for determining an estimated synergy score based on the first synergy score, and

storing the mathematical model in a machine readable memory.

7. The method of claim 6, wherein the generating a mathematical model for determining an estimated synergy score is further based on data selected from the group consisting of data representing one or more additional synergy scores associated with the paid portion of the search advertising campaign, data representing one or more synergy scores associated with one or more other paid portions of other search advertising campaigns, data representing one or more rankings of one or more websites in one or more organic listings at one or more search engines during one or more periods of time, data representing one or more rankings of the website in one or more paid search listings at one or more search engines during one or more periods of time, data representing one or more click-through-rates associated with one or more organic listings of the website at one or more search engines, data representing one or more click-through-rates associated with one or more paid search listings of the website at one or more search engines, data representing structure of the website, data representing structure of one or more other websites and data representing a semantic similarity of text associated with one or more organic listings of one or more websites at one or more search engines and text associated with one or more paid search listings of the website at one or more search engines.

8. The method of claim 6, wherein the mathematical model is generated using linear regression technique.

9. The method of claim 6, wherein the mathematical model is generated using neural network technique.

10. The method of claim 6, further comprising:

estimating, using mathematical model, an estimated synergy score.

11. The method of claim 10, further comprising:

comparing the first synergy score to the estimated synergy score; and

responsive to the comparing, generating a second synergy score.

12. The method of claim 1, further comprising:

determining a value of the first change based at least in part on the first synergy score, a revenue associated with the paid portion, and a cost associated with the paid portion.

13. The method of claim 12, wherein the value is determined by dividing the revenue by the cost to generate a resulting quotient and multiplying the resulting quotient by a scaling factor based on the first synergy score.

14. The method of claim 12, wherein the value is determined by dividing the cost by the revenue to generate a resulting quotient and multiplying the resulting quotient by a scaling factor based on the first synergy score.

15. The method of claim 12, further comprising:

determining, based on the value, an adjustment to be made to the paid portion.

16. The method of claim 1 wherein the processing includes generating a first synergy score based at least in part upon a relationship (R) comprising:

R=(TO2−

TO1)/(TP2−

TP1)

wherein TO1 represents volume of search traffic from the unpaid portion before the first change, TO2 represents volume of search traffic from the unpaid portion after the first change, TP1 represents volume of search traffic from the paid portion before the first change, TP2 represents volume of search traffic from the paid portion after the first change.

17. A non-transitory computer readable medium storing computer executable instructions which when executed on a computer simulate a process, the instructions comprising instructions to:

identify a first change made by an advertiser to a paid portion of the search advertising campaign, the first change affecting a cost of the paid portion;

determine one or more effects of the first change, the one or more effects being indicative of;

a change in a volume of search traffic resulting from the paid portion, and

a change in a volume of search traffic resulting from an unpaid portion of the search advertising campaign;

process the one or more determined effects to generate a first synergy score, wherein the first synergy score quantifies an impact of the first change on the volume of search traffic resulting from the unpaid portion; and

store the first synergy score in a machine readable memory in association with an indication of the first change.

18. The computer readable medium of claim 17, wherein the first change includes a change selected from the group consisting of a start of advertising for at least a first keyword, a stoppage of advertising for at least a second keyword, a change to a maximum cost-per-click bid for at least a third keyword, a change to a budget limit for at least a fourth keyword, and a change to a time period during which an advertisement is shown in relation to at least a fifth keyword.

19. The computer readable medium of claim 17, wherein the one or more determined effects further include one or more effects selected from the group consisting of:

one or more changes to one or more volumes of traffic from one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines,

one or more changes to one or more click-through-rates associated with one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines,

one or more changes to one or more volumes of orders associated with one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines,

one or more changes to revenue associated with one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines,

one or more changes to one or more number of page views associated with one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines, and

one or more changes to one or more whitepaper downloads associated with one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines.

20. The computer readable medium of claim 19, wherein the instructions to process the one or more determined effects includes instructions to compare a difference between a volume of traffic from an organic listing of the website at a search engine during a time period existing before the first change and a volume of traffic from an organic listing of the website at the search engine during a time period existing after the first change to a difference between a volume of traffic from a paid search listing of the website at the search engine during the time period existing before the first change and a volume of traffic from a paid search listing of the website at the search engine during the time period existing after the first change, or to plot, over a period of time, a relationship between a plurality of the one or more changes to the one or more click-through-rates associated with the one or more organic listings of the website at the one or more search engines and a corresponding plurality of the one or more changes to the one or more click-through-rates associated with the one or more paid search listings of the website at the one or more search engines.

21. The computer readable medium of claim 17, wherein the instructions further comprise instructions to:

generate a mathematical model for determining an estimated synergy score based on the first synergy score and data selected from the group consisting of data representing one or more additional synergy score associated with the paid portion of the search advertising campaign, data representing one or more synergy scores associated with one or more other paid portions of other search advertising campaigns, data representing one or more ranking of one or more websites in one or more organic listings at one or more search engines during one or more periods of time, data representing one or more ranking of the website in one or more paid search listings at one or more search engines during one or more periods of time, data representing one or more click-through-rates associated with one or more organic listings of the website at one or more organic listings of the website at one or more search engines, data representing one or more click-through-rates associated with one or more paid search listings of the website at one or more search engines, data representing structure of the website, data representing structure of one or more other websites and data representing a sematic similarity of text associated with one or more organic listings of one or more websites at one or more search engines and text associated with one or more paid search listings of the website at one or more search engine; and

store the mathematical model in a machine readable memory.

22. The computer readable medium of claim 21, wherein the mathematical model is generated using a linear regression technique or neural network technique.

23. The computer readable medium of claim 21, wherein the instructions further comprise instructions to:

estimate, using the mathematical model, an estimated synergy score.

24. The computer readable medium of claim 23, wherein the instructions further comprise instructions to:

compare the first synergy score to the estimated synergy score; and

responsive to the comparison, generate a second synergy score.

25. The computer readable medium of claim 17, wherein the instructions further comprise instructions to:

determine a value of the first change based at least in part on the first synergy score, a revenue associated with the paid portion, and a cost associated with the paid portion.

26. The computer readable medium of claim 25, wherein the value is determined by dividing the revenue by the cost to generate a resulting first quotient and multiplying the resulting first quotient by a scaling factor based on the first synergy score or by dividing the cost by the revenue to generate a resulting second quotient and multiplying the resulting second quotient by a scaling factor based on the first synergy score.

27. The computer readable medium of claim 25, wherein the instructions further comprise instructions to:

determine, based on the value, an adjustment to be made to the paid portion.

28. The computer readable medium of claim 17, wherein the processing includes generating a first synergy score based at least in part upon a relationship (R) comprising:

R=(TO2−

TO1)/(TP2−

TP1)

wherein TO1 represents volume of search traffic from the unpaid portion before the first change, TO2 represents volume of search traffic from the unpaid portion after the first change, TP1 represents volume of search traffic from the paid portion before the first change, TP2 represents volume of search traffic from the paid portion after the first change.

29. A system for measuring an impact of a change to a paid portion of a search advertising campaign that is associated with a website, comprising:

at least one processor;

a network interface;

a memory, operatively coupled to the processor, for storing logical instructions wherein execution of the logical instruction by the processor results in performing of at least the following operations;

identifying a first change made by an advertiser to the paid portion of the search advertising campaign, the first change affecting a cost of the paid portion;

determining one or more effects of the first change, the one or more effects being indicative of;

a change in a volume of search traffic resulting from the paid portion, and

a change in a volume of search traffic resulting from an unpaid portion of the search advertising campaign;

processing the one or more determined effects to generate a first synergy score, wherein the first synergy score quantifies an impact of the first change on the volume of search traffic resulting from the unpaid portion; and

storing the first synergy score in a machine readable memory in association with an indication of the first change.

30. The system of claim 29, wherein the first change includes a change selected from the group consisting of a start of advertising for at least a first keyword, a stoppage of advertising for at least a second keyword, a change to a maximum cost-per-click bid for at least a third keyword, a change to a budget limit for at least a fourth keyword, and a change to a time period during which an advertisement is shown in relation to at least a fifth keyword.

31. The system of claim 29, wherein the one or more determined effects further includes one or more effects selected from the group consisting of:

one or more changes to one or more volumes of traffic from one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines,

one or more changes to one or more click-through-rates associated with one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines,

one or more changes to one or more volumes of orders associated with one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines,

one or more changes to revenue associated with one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines,

one or more changes to one or more number of page views associated with one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines, and

one or more changes to one or more whitepaper downloads associated with one or more organic listings, paid search listings or organic and paid search listings of the website at one or more search engines.

32. The system of claim 31, wherein the processing the one or more determined effects includes comparing a difference between a volume of traffic from an organic listing of the website at a search engine during a time period existing before the first change and a volume of traffic from an organic listing of the website at the search engine during a time period existing after the first change to a difference between a volume of traffic from a paid search listing of the website at the search engine during the time period existing before the first change and a volume of traffic from a paid search listing of the website at the search engine during the time period existing after the first change, or to plotting, over a period of time, a relationship between a plurality of the one or more changes to the one or more click-through-rates associated with the one or more organic listings of the website at the one or more search engines and a corresponding plurality of the one or more changes to the one or more click-through-rates associated with the one or more paid search listings of the website at the one or more search engines.

33. The system of claim 29, wherein the execution of the logical instructions by the processor resulting in the performing of at least the following additional operations:

generating a mathematical model for determining an estimated synergy score based on the first synergy score; and

storing the mathematical model in a machine readable memory.

34. The system of claim 33, wherein the generating a mathematical model for determining an estimated synergy score is further based on data selected from the group consisting of data representing one or more additional synergy score associated with the paid portion of the search advertising campaign, data representing one or more synergy scores associated with one or more other paid portions of other search advertising campaigns, data representing one or more ranking of one or more websites in one or more organic listings at one or more search engines during one or more periods of time, data representing one or more rankings of the website in one or more paid search listings at one or more search engines during one or more periods of time, data representing one or more click-through-rates associated with one or more organic listings of the website at one or more organic listings of the website at one or more search engines, data representing one or more click-through-rates associated with one or more paid search listings of the website at one or more search engines, data representing structure of the website, data representing structure of one or more other websites and data representing a sematic similarity of text associated with one or more organic listings of one or more websites at one or more search engines and text associated with one or more paid search listings of the website at one or more search engine.

35. The system of claim 33, wherein the mathematical model is generated using a linear regression technique or a neural network technique.

36. The system of claim 33, wherein the execution of the logical instructions by the processor results in the performing of at least the following additional operations:

estimating, using the mathematical model, an estimated synergy score.

37. The system of claim 36, wherein the execution of the logical instructions by the processor results in the performing of at least the following additional operations:

comparing the first synergy score to the estimated synergy score; and

responsive to the comparing, generating a second synergy score.

38. The system of claim 29, wherein the execution of the logical instructions by the processor results in the performing of at least the following additional operations:

determining a value for the first change based at least in part on the first synergy score, a revenue associated with the paid search campaign, and a cost associated with the paid search campaign.

39. The system of claim 38, where the value is determined by dividing the revenue by the cost to generate a resulting first quotient and multiplying the resulting first quotient by a scaling factor based on the first synergy score or by dividing the cost by the revenue to generate a resulting second quotient and multiplying the resulting second quotient by a scaling factor based on the first synergy score.

40. The system of claim 38, wherein the execution of the logical instructions by the processor results in the performing of at least the following additional operation:

determining, based on the value, an adjustment to be made to the paid portion.

41. The system of claim 29, wherein the processing includes generating a first synergy score based at least in part upon a relationship (R) comprising:

R=(TO2−

TO1)/(TP2−

TP1)

wherein TO1 represents volume of search traffic from the unpaid portion before the first change, TO2 represents volume of search traffic from the unpaid portion after the first change, TP1 represents volume of search traffic from the paid portion before the first change, TP2 represents volume of search traffic from the paid portion after the first change.

42. A system, comprising:

at least one processor;

a network interface;

one or more memories, operatively coupled to the processor, for storing logical instructions wherein execution of the logical instructions by the processor results in the performing of at least the following operations;

receiving, through the network interface during a first period of time, first traffic data and second traffic data measured by a Web analytic system wherein the first traffic data is indicative of search traffic to a website resulting from a paid portion of a search advertising campaign and the second traffic data is indicative of search traffic to the website resulting from an unpaid portion of the search advertising campaign;

making a change to the paid portion of the search advertising campaign in order to create a modified advertising campaign, the change being initiated by an advertiser and affecting a cost of the paid portion;

receiving, during a second period of time, third traffic data and fourth traffic data wherein the third traffic data is indicative of search traffic associated with a paid portion of the modified advertising campaign and the fourth traffic data is indicative of search traffic associated with an unpaid portion of the modified advertising campaign;

generating a synergy score based upon the at least first traffic data, the second traffic data, the third traffic data and the fourth traffic data, wherein the synergy score quantifies an impact of the change on the at least one of a volume of traffic to the website resulting from the paid portions and the value of the traffic to the website resulting from the unpaid portions; and

storing the synergy score in the one or more memories in association with an indication of the change.

43. The system of claim 42 wherein the generating includes determining the synergy score based at least in part upon a relationship (R) comprising:

R=(TO2−

TO1)/(TP2−

TP1)

wherein TO1 represents the second traffic data, TO2 represents the fourth traffic data, TP1 represents the first traffic data and TP2 represents the third traffic data.

44. The system of claim 42 wherein the volume of traffic comprises traffic arising from unpaid search listings.

45. The system of claim 42 wherein the change comprises beginning advertising for at least a first keyword.

46. The system of claim 45 wherein the change further comprises discontinuing advertising for at least a second keyword.

47. The system of claim 42 wherein the change comprises discontinuing advertising for at least one keyword.

48. The system of claim 42 wherein the change comprises modifying a maximum cost-per-click bid for at least one keyword.

49. The system of claim 42 wherein the change comprises modifying a change to a budget limit for at least one keyword.

50. The system of claim 42 wherein the change comprises modifying a time period during which an advertisement is shown in relation to at least one keyword.