Real-time bidding system that achieves desirable cost per engagement

Patent metadata

Field	Value
Publication number	US-10949893-B2
Application number	US-201916572299-A
Country	US
Kind code	B2
Filing date	Sep 16, 2019
Priority date	Aug 26, 2014
Publication date	Mar 16, 2021
Grant date	Mar 16, 2021

Abstract

Systems and methods are disclosed for optimizing an online advertising campaign both before the campaign begins, and dynamically during the campaign. Optimizations are performed comparatively between a plurality of MPs (Media Properties) based on their relative cost-per-engagement. Comparisons are performed by first stack ranking MP inventory including any of sites, feeds, and verticals, based on cost per engagement. Once ranked, scores are assigned to the targeted inventory and a mean score is determined. Then, the inventory is rated as high, normal, or low impact based on their scores compared with the mean and a standard deviation for all scores. Higher impact sites with scores at least a standard deviation above the mean are initially favored, and the MP targeting strategy is dynamically adjusted during the campaign based on periodically re-evaluating the MP rankings, frequencies of engagement, and campaign progress relative to fulfillment in an allotted run time.

First claim

What is claimed is:

1. In a digital medium environment of real-time bidding and selection of advertisement opportunities corresponding to viewers simultaneously accessing websites via computing devices, a computerized method for dynamically allocating bids between media properties to determine an efficient bidding strategy for an online advertising campaign, comprising:
determining a set of media properties to be targeted for an online advertising campaign based on an impact level of each media property, wherein the impact level of a given media property is based on a score for the given media property in comparison to a mean score and a standard deviation value of scores of the set of media properties;
allocating a number of bids for bidding on advertising impression opportunities to a first media property comprising a higher impact level compared to a second media property;
executing the online advertising campaign in real-time by placing bids for the first media property based on the allocated number of bids; and
during real-time execution of the online advertising campaign:
determining a first engagement rate for the first media property utilizing tracked user interactions corresponding to the first media property;
determining a second engagement rate for the second media property utilizing tracked user interactions corresponding to the second media property; and
upon determining that the second engagement rate is higher than the first engagement rate:
allocating a portion of the allocated number of bids from the first media property to the second media property; and
dynamically switching media properties by placing bids for the second media property based on the portion of the allocated number of bids from the first media property to the second media property.

2. The computerized method of claim 1 , further comprising:
accumulating over a plurality of online advertising auctions a historical database including at least a cost per engagement for each of a plurality of media properties;
assigning a score for each media property with respect to at least its historical cost per engagement;
and
rating each media property to determine an impact level by comparing the score for each media property with respect to the mean score and the standard deviation value.

3. The computerized method of claim 2 , further comprising determining an impact level for a media property based on a position of a media property score from the mean score in terms of the standard deviation value.

4. The computerized method of claim 2 , wherein accumulating over the plurality of online advertising auctions the historical database including at least the cost per engagement for each of the plurality of media properties comprises accumulating the historical database only for advertising campaigns of an advertiser associated with the online advertising campaign.

5. The computerized method of claim 1 , wherein determining the first engagement rate for the first media property comprises determining how frequently an engagement event occurs on the first media property.

6. The computerized method of claim 1 , further comprising allocating the portion of the allocated number of bids from the first media property to the second media property in order to increase a probability of reaching a threshold number of engagements during a prescribed run time of the online advertising campaign.

7. The computerized method of claim 1 , further comprising allocating a subset of the portion of the allocated number of bids from shifted from the first media property to the second media property back to the first media property in order to avoid reaching a threshold number of engagements during a prescribed run time of the online advertising campaign prematurely with respect to the prescribed run time.

8. A system for dynamically allocating bids between media properties to determine an efficient bidding strategy for an online advertising campaign in a digital medium environment of real-time bidding and selection of advertisement opportunities corresponding to viewers simultaneously accessing websites via computing devices, the system comprising:
at least one processor; and
at least one non-transitory computer-readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the system to:
determine a set of media properties to be targeted for an online advertising campaign based on an impact level of each media property, wherein the impact level of a given media property is based on a score for the given media property in comparison to a mean score and a standard deviation value of scores of the set of media properties;
allocate a number of bids for bidding on advertising impression opportunities to a first media property comprising a higher impact level compared to a second media property;
execute the online advertising campaign in real-time by placing bids for the first media property based on the allocated number of bids; and
during real-time execution of the online advertising campaign:
determine a first engagement rate for the first media property utilizing tracked user interactions corresponding to the first media property;
determine a second engagement rate for the second media property utilizing tracked user interactions corresponding to the second media property;
upon determining that the second engagement rate is higher than the first engagement rate:
allocate a portion of the allocated number of bids from the first media property to the second media property; and
dynamically switch media properties by placing bids for the second media property based on the portion of the allocated number of bids from the first media property to the second media property.

9. The system of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the system to:
accumulate over a plurality of online advertising auctions a historical database including at least a cost per engagement for each of a plurality of media properties;
assign a score for each media property with respect to at least its historical cost per engagement;
and
rate each media property to determine an impact level by comparing the score for each media property with respect to the mean score.

10. The system of claim 9 , further comprising instructions that, when executed by the at least one processor, cause the system to rate each media property to determine the impact level by comparing the score for each media property with respect to the mean score by:
rating each media property to determine the impact level by comparing the score for each media property with the mean score and the standard deviation value.

11. The system of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the system to rate a media property with a score more than one standard deviation value above the mean score with a higher impact level.

12. The system of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the system to rate a media property with a score within one standard deviation value of the mean score with a normal impact level.

13. The system of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the system to rate a media property with a score more than one standard deviation value below the mean score with a lower impact level.

14. A non-transitory computer readable medium for dynamically allocating bids between media properties to determine an efficient bidding strategy for an online adver

Assignees

• Adobe Inc

Inventors

• Thakkar Kevin
• Trenkle John M
• Hughes John
• Rose Adam
• Lopatecki Jason

Classifications

• G06Q30/0275 Primary

  Auctions · CPC title

• G06Q30/0249

  based upon budgets or funds · CPC title

• G06Q30/0242

  Determining effectiveness of advertisements · CPC title