Methods for determining targeting parameters and bids for online ad distribution

Patent metadata

Field	Value
Publication number	US-10521828-B2
Application number	US-201615176760-A
Country	US
Kind code	B2
Filing date	Jun 8, 2016
Priority date	Jun 8, 2016
Publication date	Dec 31, 2019
Grant date	Dec 31, 2019

Abstract

Systems and methods are disclosed herein for distributing online ads with electronic content according to online ad request targeting parameters. One embodiment of this technique involves placing online test ads across multiple online ad request dimensions and tracking a performance metric for the online test ads. The performance of the online ad request dimensions is estimated based on the tracking of the performance metric for the online test ads and online ad request targeting parameters are established for spending a budget of a campaign to place online ads in response to online ad requests having particular online ad request dimensions. Online ads are then distributed based on using the online ad request targeting parameters to select online ad requests.

First claim

What is claimed is:

1. A method for distributing online ads with electronic content according to online ad request targeting parameters, the method comprising:
placing online test ads across multiple online ad request dimensions, where the online ad request dimensions represent multiple attributes of online ad requests;
tracking a performance metric for the online test ads;
estimating, via a processor, performance of the online ad request dimensions based on the tracking of the performance metric for the online test ads;
establishing, via the processor, online ad request targeting parameters for spending a budget of a campaign to place online ads in response to online ad requests having particular online ad request dimensions; and
distributing online ads to ad recipients based on using the online ad request targeting parameters to select online ad requests, wherein distributing the online ad requests places online ads in response to the selected online ad requests, wherein the targeting parameters are established by:
building a regression tree with online ad request dimensions as independent variables and the performance metric as a dependent variable,
identifying a first online ad request dimension that best distinguishes performance according to the performance metric, the performance metric representing revenue per thousand impressions (RPMs),
creating a first layer of nodes in the regression tree for values of the first online ad request dimension,
for each of the first layer of nodes, identifying a respective second online ad request dimension based on RPMs and creating sub-nodes to the first layer of nodes for values for the respective online ad request dimension, and
identifying targets comprising targeted combinations of online ad request dimensions based on paths from a root of the regression tree to leaf nodes of the regression tree, wherein the leaf nodes with low RPMs representing non-performing online ad request dimensions are not considered.

2. The method of claim 1 , wherein online ad request dimension values are grouped based on similar performance.

3. The method of claim 1 , wherein the number of targets is identified based on the budget and historical spend and performance data.

4. The method of claim 1 further comprising automatically determining bid values for targets based on the estimating of performance of the online ad request dimensions.

5. The method of claim 1 further comprising performing the method on a daily basis to allocate a daily budget to current day online ad request targets.

6. The method of claim 1 further comprising:
identifying online ad request targets based on the online ad request targeting parameters;
determining bid landscapes for individual online ad request targets, the bid landscapes identifying an expected performance metric for different incurred bid costs;
executing an optimization to determine bid values for the online ad request targets to spend a campaign budget to maximize the performance metric; and
distributing the online ads with the electronic content in accordance with the identified online ad request targets and determined bid values for the online ad request targets.

7. A computer program product for distributing online ads with electronic content according to online ad request targeting parameters, the computer program product being tangibly embodied on a non-transitory computer-readable storage medium and comprising instructions that, when executed by at least one computing device, are configured to cause the at least one computing device to:
place online test ads across multiple online ad request dimensions, where the online ad request dimensions represent multiple attributes of online ad requests;
track a performance metric for the online test ads;
estimate performance of the online ad request dimensions based on the tracking of the performance metric for the online test ads;
establish online ad request targeting parameters for spending a budget of a campaign to place online ads in response to online ad requests having particular online ad request dimensions; and
distribute online ads to ad recipients based on using the online ad request targeting parameters to select online ad requests, wherein distributing the online ad requests places online ads in response to the selected online ad requests, wherein the targeting parameters are established by:
building a regression tree with online ad request dimensions as independent variables and the performance metric as a dependent variable,
identifying a first online ad request dimension that best distinguishes performance according to the performance metric, the performance metric representing revenue per thousand impressions (RPMs),
creating a first layer of nodes in the regression tree for values of the first online ad request dimension,
for each of the first layer of nodes, identifying a respective second online ad request dimension based on RPMs and creating sub-nodes to the first layer of nodes for values for the respective online ad request dimension, and
identifying targets comprising targeted combinations of online ad request dimensions based on paths from a root of the regression tree to leaf nodes of the regression tree, wherein the leaf nodes with low RPMs representing non-performing online ad request dimensions are not considered.

8. The computer program product of claim 7 , wherein online ad request dimension values are grouped based on similar performance.

9. The computer program product of claim 7 , wherein the number of targets is identified based on the budget and historical spend and performance data.

10. The computer program product of claim 7 further comprising instructions that, when executed by the at least one computing device, are configured to cause the at least one computing device to automatically determine bid values for targets based on the estimating of performance of the online ad request dimensions.

11. The computer program product of claim 7 further comprising instructions that, when executed by the at least one computing device, are configured to cause the at least one computing device to perform the instructions on a daily basis to allocate a daily budget to current day online ad request targets.

12. The computer program product of claim 7 further comprising instructions that, when executed by the at least one computing device, are configured to cause the at least one computing device to:
identify online ad request targets based on the online ad request targeting parameters;
determine bid landscapes for individual online ad request targets, the bid landscapes identifying an expected performance metric for different incurred bid costs;
execute an optimization to determine bid values for the online ad request targets to spend a campaign budget to maximize the performance metric; and
distribute the online ads with the electronic content in accordance with the identified online ad request targets and determined bid values for the online ad request targets.

13. A system for distributing online ads with electronic content according to online ad request targeting parameters, the system comprising:
at least one memory including instructions; and
at least one processor that is operably coupled to the at least one memory and that is arranged and configured to execute the instructions that, when executed, cause the at least one processor to:
place online test ads across multiple online ad request dimensions, where the online ad request dimensions represent multiple attributes of online ad requests;
track a performance metric for the online test ads;
estimate performance of the online

Assignees

• Adobe Inc

Inventors

• Pai Deepak
• Nguyen Trung
• Wang Sy Bor
• Mathew Jose
• Pani Abhishek
• Gupta Neha

Classifications

• G06Q30/0277

  Online advertisement · CPC title

• G06Q30/0275 Primary

  Auctions · CPC title