PROFILE RECOMMENDATIONS FOR ADVERTISEMENT CAMPAIGN PERFORMANCE IMPROVEMENT

• US 20110035273A1
• Filed: 08/05/2009
• Published: 02/10/2011
• Est. Priority Date: 08/05/2009
• Status: Abandoned Application

• Current Assignee: Oath Inc. (Verizon Communications Inc.)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Narayanan, Vijay Krishna, Parekh, Rajesh, Wan, Xia, Parikh, Jignashu, Bhatt, Rushi P.
• Application Number:
  US12/536,334
• Publication Number:
  US 20110035273A1
• Time in Patent Office: Days
• US Class Current: 705/14.42
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0243 Comparative campaigns

Abstract

A method for recommending improvements to advertisement campaign performance includes receiving a seed campaign insertion order (IO) having one or more campaign IO lines; computing a plurality of neighbor ad campaigns based on comparison of the seed campaign IO with a dataset of advertiser ad campaign IO lines; generating campaign IO recommendations by executing an algorithm to recommend profiles to add to the seed campaign IO from booking lines corresponding to the profiles based on performance of such use by the neighbor ad campaigns being generally above average when compared with campaigns that did not use the recommended profiles; filtering the profile recommendations based on a plurality of performance-enhancing criteria of the seed campaign IO and the neighbor ad campaigns with respect to each potential profile recommendation; ranking the profile recommendations based on at least one performance metric; and displaying the ranked profile recommendations to the advertiser for selection.

Claims

1. An advertisement campaign performance improvement recommendation system comprising:

a server having a processor and system memory, wherein to improve performance of a seed campaign insertion order (IO), the processor is configured to;

(a) receive the seed campaign IO, which includes one or more campaign IO lines of an advertiser;

(b) compute a plurality of neighbor advertisement (ad) campaigns based on a comparison of the seed campaign IO with a dataset of advertiser ad campaigns IO lines by (i) processing campaign booking and performance information associated with ad campaigns previously booked by a publisher, and (ii) applying thereto a statistical document clustering technique;

(c) generate campaign IO recommendations by executing an algorithm to recommend profiles to add to the seed campaign IO from booking lines corresponding to the profiles based on performance of such use by the neighbor ad campaigns being generally above average when compared with campaigns that did not use the recommended profiles;

(d) filter the profile recommendations based on a plurality of performance-enhancing criteria of the seed campaign IO and the neighbor ad campaigns with respect to each potential profile recommendation;

(e) rank the profile recommendations based on a performance metric; and

(f) display the ranked profile recommendations to the advertiser for selection.

2. The system of claim 1, wherein the performance metric comprises a conversion rate, click-through rate (CTR), cost per click (CPC), cost per acquisition (CPA), return on investment (ROI), or a combination thereof.

3. The system of claim 2, wherein the performance-enhancing criteria comprises a criterion that a profile recommendation has not been run by the advertiser before or that a profile recommendation, within the neighbor ad campaigns, has outperformed other ad campaigns as measured by a performance metric.

4. The system of claim 2, wherein the processor is further configured to predict a performance metric of the seed campaign IO based on the adoption of one or more of the filtered profile recommendations.

5. The system of claim 2, wherein to filter the profile recommendations, the processor further:

determines profile recommendations (A, B) within the neighbor ad campaigns that co-occur therein more than a pre-specified threshold number of times, wherein recommendation profile A has been used previously in an ad campaign by the advertiser, and recommendation profile B has not been used previously in an ad campaign by the advertiser;

determines whether profile recommendation B has outperformed profile recommendation A within the neighbor ad campaigns according to a performance metric; and

eliminates the profile recommendation B if it does not outperform profile recommendation A.

6. The system of claim 2, further comprising:

a network interface configured to receive data feeds over a network, the data feeds including campaign insertion order (IO) lines and advertisement user log data associated therewith, wherein the network interface is coupled with the processor; and

at least one database coupled with the processor configured to store the campaign IO lines and the advertisement user log data, wherein the performance-enhancing criteria comprises a criterion that a profile recommendation exceeds a pre-specified performance threshold within the neighbor ad campaigns.

7. The system of claim 6, wherein the neighbor ad campaigns are derived from a dataset of ad campaign IOs, wherein to generate the campaign IO recommendations, the processor, for each neighbor ad campaign, is further configured to:

(a) aggregate clicks and impressions from the advertisement user log data to compute an average of a performance metric for each profile that occurs in lines of the neighbor ad campaign;

(b) for each of a plurality of profiles in the neighbor ad campaign;

(1) determine if an average of the performance metric of the profile is greater than or equal to an average of the performance metric of the neighbor ad campaigns plus a first predetermined constant;

(2) determine if an average of the performance metric of the profile is greater than or equal to the average of the performance metric of the profile determined globally for the entire dataset plus a second predetermined constant;

(c) aggregate clicks and impressions to compute the performance metric of each qualifying profile in (b) (set Q) across all IO'"'"'s within the neighbor ad campaigns.

8. The system of claim 7, wherein the first predetermined constant comprises about 0.8 times the standard deviation of the performance metric of all IOs within the neighbor ad campaigns, and wherein the second predetermined constant comprises about 0.8 times the standard deviation of the performance metric of the dataset of ad campaign IOs.

9. The system of claim 7, wherein to filter the profile recommendations, the processor, for every profile in set Q:

removes qualifying profiles that have total impressions less than a minimum threshold of impressions based on impressions obtained from the advertisement user logs data; and

removes qualifying profiles that have been used by less than a minimum number of advertisers within the dataset, as determined from the advertisement user logs data.

10. The system of claim 6, wherein the neighbor ad campaigns are derived from a dataset of ad campaign IOs, wherein to generate the campaign IO recommendations, the processor is further configured to:

(a) create a union of related profiles over all profiles of the seed campaign IO and the neighbor ad campaigns;

(b) determine a set A of pairs of profiles <

p₁, p₂>

in the union that are commonly booked together in campaign IOs, including their respective affinity scores;

(c) identify a set C equal to {p₂|<

p₁, p₂>

ε

A, p₁ε

IO i} of recommendations based on the profiles in the seed campaign IO;

(d) choose a top N profiles from the candidate set C based on their respective affinity score; and

(e) sort the filtered top N profiles by a performance metric to be displayed to the advertiser for selection.

11. A computer-implemented method for advertisement campaign performance improvement comprising:

(a) receiving, by a server from an advertiser, a seed campaign insertion order (IO) having one or more campaign IO lines;

(b) computing, by a processor coupled with the server, a plurality of neighbor advertisement (ad) campaigns based on comparison of the seed campaign IO with a dataset of advertiser ad campaign IO lines by (i) processing campaign booking and performance information associated with ad campaigns previously booked by a publisher, and (ii) applying thereto a statistical document clustering technique;

(c) generating, by the processor, campaign IO recommendations by executing an algorithm to recommend profiles to add to the seed campaign IO from booking lines corresponding to the profiles based on performance of such use by the neighbor ad campaigns being generally above average when compared with campaigns that did not use the recommended profiles;

(e) filtering, by the processor, the profile recommendations based on a plurality of performance-enhancing criteria of the seed campaign IO and the neighbor ad campaigns with respect to each potential profile recommendation;

(d) ranking, by the processor, the profile recommendations based on at least one performance metric; and

(f) displaying, by the processor, the ranked profile recommendations to the advertiser for selection.

12. The method of claim 11, wherein the performance metric comprises a conversion rate, click-through rate (CTR), cost per click (CPC), cost per acquisition (CPA), return on investment (ROI), or a combination thereof, the method further comprising:

predicting a performance metric of the seed campaign IO based on the adoption of one or more of the filtered profile recommendations.

13. The method of claim 12, wherein the performance-enhancing criteria comprises a criterion that a profile recommendation has not been run by the advertiser before or that a profile recommendation, within the neighbor ad campaigns, has outperformed other ad campaigns as measured by a performance metric.

14. The method of claim 12, wherein to filter the profile recommendations, the method further comprising:

determining profile recommendations (A, B) within the neighbor ad campaigns that co-occur therein more than a pre-specified threshold number of times, wherein recommendation profile A has been used previously in an ad campaign by the advertiser, and recommendation profile B has not been used previously in an ad campaign by the advertiser;

determining whether profile recommendation B has outperformed profile recommendation A within the neighbor ad campaigns according to a performance metric; and

eliminating the profile recommendation B if it does not outperform profile recommendation A.

15. The method of claim 12, further comprising:

retrieving, by a network interface coupled with the server, data feeds including campaign IO lines and advertisement user log data associated therewith; and

storing the campaign IO lines and the advertisement user log data in a database coupled with the server;

wherein the performance-enhancing criteria comprises a criterion that a profile recommendation exceeds a pre-specified performance threshold within the neighbor ad campaigns.

16. The method of claim 15, wherein the neighbor ad campaigns are derived from a dataset of ad campaign IOs, wherein to generate the campaign IO recommendations, the method further comprising, for each neighbor ad campaign:

(a) aggregating clicks and impressions from the advertisement user log data to compute an average of a performance metric for each profile that occurs in lines of the neighbor ad campaign;

(b) for each of a plurality of profiles in the neighbor ad campaign;

(1) determining if an average of the performance metric of the profile is greater than or equal to an average of the performance metric of the neighbor ad campaigns plus a first predetermined constant;

(2) determining if an average of the performance metric of the profile is greater than or equal to the average of the performance metric of the profile determined globally for the entire dataset plus a second predetermined constant;

(c) aggregating clicks and impressions to compute the performance metric of each qualifying profile in (b) (set Q) across all IO'"'"'s within the neighbor ad campaigns.

17. The method of claim 16, wherein the first predetermined constant comprises about 0.8 times the standard deviation of the performance metric of all IOs within the neighbor ad campaigns, and wherein the second predetermined constant comprises about 0.8 times the standard deviation of the CTR of the dataset of ad campaign IOs.

18. The method of claim 16, wherein to filter the profile recommendations, the method, for every profile in set Q, further comprises:

removing qualifying profiles that have total impressions less than a minimum threshold of impressions based on impressions obtained from the advertisement user logs data; and

removing qualifying profiles that have been used by less than a minimum number of advertisers within the dataset, as determined from the advertisement user logs data.

19. The method of claim 15, wherein the neighbor ad campaigns are derived from a dataset of ad campaign IOs, wherein to generate the campaign IO recommendations, the method further comprising:

(a) creating a union of related profiles over all profiles of the seed campaign IO and the neighbor ad campaigns;

(b) determining a set A of pairs of profiles <

p₁, p₂>

in the union that are commonly booked together in campaign IOs, including their respective affinity scores;

(c) identifying a set C equal to {p₂|<

p₁, p₂>

ε

A, p₁ε

IO i} of recommendations based on the profiles in the seed campaign IO;

(d) choosing a top N profiles from the candidate set C based on their respective affinity score; and

(e) sorting the filtered top N profiles by a performance metric to be displayed to the advertiser for selection.

20. A computer-readable storage medium comprising a set of instructions, the set of instructions to direct a processor to perform the acts of:

(a) receiving a seed campaign insertion order (IO) having one or more campaign IO lines;

(b) computing a plurality of neighbor advertisement (ad) campaigns based on comparison of the seed campaign IO with a dataset of advertiser ad campaign IO lines by (i) processing campaign booking and performance information associated with ad campaigns previously booked by a publisher, and (ii) applying thereto a statistical document clustering technique;

(c) generating campaign IO recommendations by executing an algorithm to recommend profiles to add to the seed campaign IO from booking lines corresponding to the profiles based on performance of such use by the neighbor ad campaigns being generally above average when compared with campaigns that did not use the recommended profiles;

(e) filtering, the profile recommendations based on a plurality of performance-enhancing criteria of the seed campaign IO and the neighbor ad campaigns with respect to each potential profile recommendation;

(d) ranking, by the processor, the profile recommendations based on at least one performance metric; and

(f) displaying, by the processor, the ranked profile recommendations to the advertiser for selection.

21. The computer-readable storage medium of claim 20, wherein the performance metric comprises a conversion rate, click-through rate (CTR), cost per click (CPC), cost per acquisition (CPA), return on investment (ROI), or a combination thereof.

22. The computer-readable storage medium of claim 21, wherein the performance-enhancing criteria comprises a criterion that a profile recommendation has not been run by the advertiser before or that a profile recommendation, within the neighbor ad campaigns, has outperformed other ad campaigns as measured by a performance metric.

23. The computer-readable storage medium of claim 21, further comprising a set of instructions to direct a processor to perform the acts of:

retrieving, by a network interface coupled with the server, data feeds including campaign IO lines and advertisement user log data associated therewith; and

storing the campaign IO lines and the advertisement user log data in a database coupled with the server;

wherein the performance-enhancing criteria comprises a criterion that a profile recommendation exceeds a pre-specified performance threshold within the neighbor ad campaigns.

24. The computer-readable storage medium of claim 23, wherein the neighbor ad campaigns are derived from a dataset of ad campaign IOs, wherein to generate the campaign IO recommendations for each neighbor ad campaign, further comprising a set of instructions to direct the processor to perform the acts of:

(a) aggregating clicks and impressions from the advertisement user log data to compute an average of a performance metric for each profile that occurs in lines of the neighbor ad campaign;

(b) for each of a plurality of profiles in the neighbor ad campaign;

(1) determining if an average of the performance metric of the profile is greater than or equal to an average of the performance metric of the neighbor ad campaigns plus a first predetermined constant;

(2) determining if an average of the performance metric of the profile is greater than or equal to the average of the performance metric of the profile determined globally for the entire dataset plus a second predetermined constant;

(c) aggregating clicks and impressions to compute the performance metric of each qualifying profile in (b) (set Q) across all IO'"'"'s within the neighbor ad campaigns.

25. The computer-readable storage medium of claim 24, wherein to filter the profile recommendations for every profile in set Q, further comprising a set of instructions to direct the processor to perform the acts of:

removing qualifying profiles that have total impressions less than a minimum threshold of impressions based on impressions obtained from the advertisement user logs data; and

removing qualifying profiles that have been used by less than a minimum number of advertisers within the dataset, as determined from the advertisement user logs data.

26. The computer-readable storage medium of claim 23, wherein the neighbor ad campaigns are derived from a dataset of ad campaign IOs, wherein to generate the campaign IO recommendations, further comprising a set of instructions to direct the processor to perform the acts of:

(a) creating a union of related profiles over all profiles of the seed campaign IO and the neighbor ad campaigns;

(b) determining a set A of pairs of profiles <

p₁, p₂>

in the union that are commonly booked together in campaign IOs, including their respective affinity scores;

(c) identifying a set C equal to {p₂|<

p₁, p₂>

ε

A, p₁ε

IO i} of recommendations based on the profiles in the seed campaign IO;

(d) choosing a top N profiles from the candidate set C based on their respective affinity score; and

(e) sorting the filtered top N profiles by a performance metric to be displayed to the advertiser for selection.