Publisher scoring

• US 20080154717A1
• Filed: 12/22/2006
• Published: 06/26/2008
• Est. Priority Date: 12/22/2006
• Status: Abandoned Application

• Current Assignee: Oath Inc. (Verizon Communications Inc.)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Dolan, Brian, Dang, Steve, Saifee, Qasim
• Application Number:
  US11/644,127
• Publication Number:
  US 20080154717A1
• Time in Patent Office: Days
• US Class Current: 705/14
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0263 based upon Internet or website rating
• CPC Class Codes: G06Q 30/0273 Determination of fees for advertising
• CPC Class Codes: G06Q 30/0277 Online advertisement

Abstract

A system and method are disclosed for a publisher scoring algorithm. Various factors or variables are analyzed for publishers to determine a score associated with the publishers. The score may be a reflection of the success or value a publisher provides to an advertisement provider or an advertiser.

Claims

1. A method of measuring quality of a publisher comprising:

receiving publisher data related to advertisements, wherein the publisher data comprises a conversion variable, an impressions variable, and a traffic quality variable; and

calculating a publisher score based on the publisher data.

2. The method according to claim 1 wherein the step of calculating a publisher score based on the publisher data comprises:

normalizing the data for each of the variables;

determining a standard deviation from the mean for each of the normalized variables;

transforming the normalized standard deviation from the mean for each of the variables;

multiplying each of the transformed variables by a weight associated with the variable; and

combining each of the weighted, transformed variables to calculate the publisher score.

3. The method according to claim 1 wherein the publisher data is related to a display of at least one advertisement on a page.

4. The method according to claim 3 wherein the page is a web page configured to be displayed on a web browser.

5. The method according to claim 1 wherein the impressions variable comprises at least one of a percent of domestic clicks, revenue per thousand (RPM), price per click (PPC) or combinations thereof.

6. The method according to claim 5 wherein the publisher data further comprises a size variable.

7. The method according to claim 6 wherein the publisher data further comprises a publisher review warnings variable, suspensions variable and terminations variable.

8. The method according to claim 6 wherein the publisher score based on the publisher data is calculated by a formula Publisher Score=f(Transformed Size SD) * (RPM weight * f(Transformed RPM SD, Transformed Conversion Rate SD)+PPC weight * f(Transformed PPC SD)+% Domestic Clicks weight * f(Transformed % Domestic Clicks SD)+Traffic Quality Score weight * f(Transformed Traffic Quality Score SD)+Volatility weight * f(Transformed Volatility SD)+Conversion Rate weight * f(Transformed Conversion Rate SD)), wherein SD is standard deviation and the function f(x) is a normalization.

9. A system calculating a publisher score comprising:

a publisher network server configured to be connected with a network and to receive the publisher data factors from publishers; and

an evaluator coupled with the publisher network server to receive publisher data factors, wherein the evaluator comprises;

a deviator for calculating the standard deviation from the mean of each of the factors;

a transformer, coupled with the deviator, for applying a function to the standard deviations from the mean for each of the factors; and

a weightor, coupled with the transformer, for applying a weight to each of the transformed standard deviations from the mean for each of the factors;

wherein the publisher score is based on the weighted transformed standard deviations for each of the factors.

10. The system according to claim 9 wherein the at least one publisher data factor comprises at least one of a conversion rate, a traffic quality, a domestic click percentage, a revenue per thousand (RPM), a volatility, or combinations thereof.

11. The system according to claim 10 wherein the at least one publisher data factor further comprises at least one of a publisher review warning, a publisher review suspension, a publisher review termination, or combinations thereof.

12. The system according to claim 9 wherein the publishers display a page, wherein the page displays at least one advertisement.

14. The system according to claim 9 further comprising a publisher network database coupled with the publisher network server and configured to store the publisher data related to the publishers.

15. The system according to claim 9 wherein the evaluator comprises a processor, wherein the processor includes the deviator, the transformer and the weightor.

16. The system according to claim 9 wherein the weight applied to each of the transformed standard deviations for each of the at least one publisher data factors reflects the relative importance of the at least one publisher data factor.

17. The system according to claim 9 wherein the weightor is configured to multiply the publisher score by a size of the publisher, wherein a larger publisher has a higher multiplier.

13. (canceled)

18. In a computer readable storage medium having stored therein data representing instructions executable by a programmed processor for determining a publisher score, the storage medium comprising instructions operative to:

gathering advertising data associated with the publisher, wherein the advertising data comprises factors including a conversion rate, a domestic click percentage, a traffic quality score, or combinations thereof, the factors associated with the publisher;

combining the factors for the publisher into a publisher raw score; and

generating the publisher score from the publisher raw score.

19. The storage medium according to claim 18 wherein the step of combining the factors further comprises:

determining a standard deviation for each factor;

transforming the standard deviation for each factor based on a predetermined function;

multiplying the transformed standard deviation for each factor by a weight associated with each factor to generate a raw score for each factor; and

combining the raw scores for each factor into the publisher raw score.

20. The storage medium according to claim 18 wherein the factors further comprise at least one of a conversion rate, a traffic quality, a domestic click percentage, a revenue per thousand (RPM), a volatility, or combinations thereof.

21. The storage medium according to claim 20 wherein the factors further comprise at least one of a publisher review warning, a publisher review suspension, a publisher review termination, or combinations thereof.

22. The storage medium according to claim 18 wherein the publisher displays a page, wherein the page displays at least one advertisement, further wherein the advertiser data is based on the at least one advertisement.

23. (canceled)

24. A method of measuring and scoring a plurality of publishers comprising:

receiving publisher data related to advertisements for each of the plurality of publishers;

calculating a publisher score based on the publisher data for each of the plurality of publishers;

comparing the publisher score for each of the plurality of publishers with one another; and

assigning a higher quality value to a publisher with a higher publisher score relative to other publishers from the plurality of publishers.

26. The method of claim 24 wherein the quality value is an indication of a likelihood of success of an advertisement with a particular publisher or an indication of desirability for advertisers to place an advertisement with a particular publisher.

27. The method of claim 26 wherein the likelihood of success of the advertisement includes an expected conversion rate of the advertisement.

28. The method of claim 24 wherein the publisher data comprises at least one of a conversion, an impression, a traffic quality, percent of domestic clicks, revenue per thousand (RPM), price per click (PPC), a publisher review warnings variable, a suspensions variable, a terminations variable, or combinations thereof.

25. (canceled)