Systems and methods for predicting and pricing of gross rating point scores by modeling viewer data

• US 10,049,382 B2
• Filed: 12/30/2013
• Issued: 08/14/2018
• Est. Priority Date: 03/13/2013
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Hughes, John, Rose, Adam, Trenkle, John M.
• Primary Examiner(s): Stoltenberg, David J
• Assistant Examiner(s): Ezewoko, Michael I
• Application Number:
  US14/143,984
• Publication Number:
  US 20140278937A1
• Time in Patent Office: 1,688 Days
• Field of Search: 705 1445
• CPC Class Codes: G06Q 30/0246 Traffic
• CPC Class Codes: G06Q 30/0273 Determination of fees for advertising

Abstract

Systems and methods are disclosed for characterizing websites and viewers, for predicting GRPs (Gross Rating Points) for online advertising media campaigns, and for pricing media campaigns according to GRPs delivered as opposed to impressions delivered. To predict GRPs for a campaign, systems and methods are disclosed for first characterizing polarized websites and then characterizing polarized viewers. To accomplish this, a truth set of viewers with known characteristics is first established and then compared with historic and current media viewing activity to determine a degree of polarity for different Media Properties (MPs)—typically websites offering ads—with respect to gender and age bias. A broader base of polarized viewers is then characterized for age and gender bias, and their propensity to visit a polarized MP is rated. Based on observed and calculated parameters, a GRP total is then predicted and priced to a client/advertiser for an online ad campaign.

Claims

1. In a digital medium environment of real-time bidding and selection of advertising opportunities corresponding to viewers simultaneously accessing websites via computing devices, a computerized method for efficiently providing bid responses and advertising over an online network, comprising:

establishing, by one or more processors, a database of polarized media properties and polarization probabilities for the polarized media properties, wherein the polarization probabilities comprise, for a first polarized media property of the polarized media properties, a first polarization probability corresponding to a first viewer characteristic and a second polarization probability corresponding to a second viewer characteristic;

receiving, by the one or more processors, desired gross rating points for an online ad campaign;

receiving targeting parameters for the online ad campaign, wherein the targeting parameters comprise targeted geographic locations, targeted polarized media properties, and targeted viewer characteristics, and wherein the targeted polarized media properties comprise the first polarized media property and the targeted viewer characteristics comprise the first viewer characteristic and the second viewer characteristic;

determining, by the one or more processors, a number of impressions to achieve the desired gross rating points for the online ad campaign based on the targeted polarized media properties, the desired gross rating points, the targeted viewer characteristics, the targeted geographic locations, and the polarization probabilities for the targeted polarized media properties in the database of polarized media properties including, for the first polarized media property, the first polarization probability corresponding to the first viewer characteristic and the second polarization probability corresponding to the second viewer characteristic;

running the online ad campaign based on the number of impressions to achieve the desired gross rating points by;

providing an advertisement for display to a first viewer, wherein the advertisement is selected using the targeting parameters;

receiving an impression opportunity from a remote server, wherein the impression opportunity references a second viewer and a media property; and

responding to the impression opportunity, by the one or more processors, by sending a bid response to the remote server based on a determination that (i) the targeting parameters match characteristics of the second viewer and the media property and (ii) the desired gross rating points have not been achieved.

2. The computerized method of claim 1, further comprising:

determining a historical cost of purchasing impressions on each targeted polarized media property of the targeted polarized media properties; and

predicting, by the one or more processors, a cost for the number of impressions to achieve the desired gross rating points for the online ad campaign, based at least in part on the historical cost of purchasing impressions on each targeted polarized media property, and the polarization probability of each targeted polarized media property with respect to each targeted viewer characteristic.

3. The computerized method of claim 2, further comprising:

determining, by the one or more processors, a price quote for the online ad campaign based on at least the predicted cost of the number of impressions to achieve the desired gross rating points for the online ad campaign and a profit margin factor.

4. The computerized method of claim 3, wherein determining the price quote comprises determining a number of impressions to purchase for the first targeted polarized media property based on desired on-target impressions, the first polarization probability for the first polarized media property with respect to the first viewer characteristic and the second polarization probability for the first polarized media property with respect to the second viewer characteristic.

5. The computerized method of claim 3, further comprising:

determining the price quote based on an efficiency factor, wherein the efficiency factor is determined based on a difference between historical gross rating points desired and historical gross rating points delivered.

6. The computerized method of claim 5, further comprising:

determining, by the at least one processor and after running the online ad campaign, an actual gross rating points delivered via the online ad campaign; and

modifying the efficiency factor by comparing the desired gross rating points with the actual gross rating points delivered via the online ad campaign.

7. The computerized method of claim 1, further comprising determining that the desired gross rating points have not been achieved by determining that the number of impressions have not been purchased.

8. The computerized method of claim 1, further comprising determining a cost of on-target impressions for one or more targeted polarized media properties based on the polarization probabilities for the one or more targeted polarized media properties and a cost of impressions for the one or more targeted polarized media properties;

and

selecting targeted polarized media properties to include in the online ad campaign based on the determined cost of on-target impressions for the one or more targeted polarized media properties.

9. The computerized method of claim 1, wherein determining the number of impressions to achieve the desired gross rating points further comprises generating a composite polarization probability for the first polarized media property based on the first polarization probability and the second polarization probability and determining the number of impressions to achieve the desired gross rating points based on the composite polarization probability for the first polarized media property.

10. The computerized method of claim 1, further comprising:

determining a cost per point for each targeted polarized media property of the targeted polarized media properties; and

selecting a set of targeted polarized media properties to include in the online ad campaign based on the determined cost per point for each targeted polarized media property.

11. The computerized method of claim 10 further comprising:

determining an available targeted inventory for the selected set of targeted polarized media properties;

determining, by aggregating the available targeted inventory, that the available targeted inventory will achieve the desired gross rating points; and

in response to determining that the available targeted inventory will achieve the desired gross rating points, generating a gross rating points quote based on the selected set of targeted polarized media properties.

12. The computerized method of claim 10 further comprising:

determining an available targeted inventory for the selected set of targeted polarized media properties;

determining, by aggregating the available targeted inventory, that the aggregated available targeted inventory will not achieve the desired gross rating points;

in response to determining that the aggregated available targeted inventory will not achieve the desired gross rating points, selecting at least one more polarized media property to add to the selected set of targeted polarized media properties; and

determining, by the one or more processors, a revised aggregated available targeted inventory based on the selected set of targeted polarized media properties, including the at least one more polarized media property; and

in response to determining that the revised aggregated available targeted inventory achieves the desired gross rating points, generating a gross rating points quote.

13. A system for efficiently providing bid responses and advertising over an online network in a digital medium environment of real-time bidding and selection of advertising 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 that, when executed by the at least one processor, cause the system to;

establish a database of polarized media properties and polarization probabilities for the polarized media properties, wherein the database comprises viewer characteristics corresponding to the polarized media properties, wherein the polarization probabilities comprise, for a first polarized media property of the polarized media properties, a first polarization probability corresponding to a first viewer characteristic and a second polarization probability corresponding to a second viewer characteristic;

receive desired gross rating points for an online ad campaign;

receive targeting parameters for the online ad campaign, wherein the targeting parameters comprise targeted geographic locations, targeted polarized media properties, and targeted viewer characteristics, and wherein the targeted polarized media properties comprise the first polarized media property and the targeted viewer characteristics comprise the first viewer characteristic and the second viewer characteristic;

determine a number of impressions to purchase to achieve the desired gross rating points for the online ad campaign based on the targeted polarized media properties, the desired gross rating points, the targeted viewer characteristics, the targeted geographic locations, and the polarization probabilities for the targeted polarized media properties in the database of polarized media properties including, for the first polarized media property, the first polarization probability corresponding to the first viewer characteristic and the second polarization probability corresponding to the second viewer characteristic;

execute the online ad campaign based on the number of impressions to achieve the desired gross rating points by;

providing an advertisement for display to a first viewer, wherein the advertisement is selected using the targeting parameters;

receiving an impression opportunity from a remote server, wherein the impression opportunity references a second viewer and a media property; and

responding to the impression opportunity by sending a bid response to the remote server based on a determination that (i) the targeting parameters match characteristics of the second viewer and the media property and (ii) the desired gross rating points have not been achieved.

14. The system of claim 13, further comprising instructions that, when executed by the at least one processor, cause the system to:

determine a historical cost of reaching viewers on each targeted polarized media property of the targeted polarized media properties; and

predict a cost for the number of impressions to achieve the desired gross rating points for the online ad campaign, based at least in part on the historical cost of reaching viewers on each targeted polarized media property and the polarization probability of each targeted polarized media property with respect to each targeted viewer characteristic.

15. The system of claim 14, further comprising instructions that, when executed by the at least one processor, cause the system to:

determine a price quote for the online ad campaign based on at least the predicted cost of the number of impressions to purchase to achieve the desired gross rating points for the online ad campaign and a profit margin factor.

16. The system of claim 15, further comprising instructions that, when executed by the at least one processor, cause the system to determine the price quote by determining a number of impressions to purchase for a targeted polarized media property based on desired on-target impressions and a polarization probability for the targeted polarized media property with respect to a targeted viewer characteristic.

17. The system of claim 15, further comprising instructions that, when executed by the at least one processor, cause the system to determine the price quote based on an efficiency factor, wherein the efficiency factor is determined based on a difference between historical gross rating points desired and historical gross rating points delivered.

18. The system of claim 17, further comprising instructions that, when executed by the at least one processor, cause the system to:

determine, after running the online ad campaign, the actual gross rating points delivered via the online ad campaign; and

modify the efficiency factor by comparing the desired gross rating points with an actual gross rating points delivered via the online ad campaign.

19. The system of claim 13, further comprising instructions that, when executed by the at least one processor, cause the system to:

determine a cost of on-target impressions for one or more targeted polarized media properties based on the polarization probabilities for the one or more targeted polarized media properties and a cost of impressions for the one or more targeted polarized media properties; and

select targeted polarized media properties to include in the online ad campaign based on the determined cost of on-target impressions for the one or more targeted polarized media properties.

20. The system of claim 13, further comprising instructions that, when executed by the at least one processor, cause the system to determine the number of impressions to purchase to achieve the desired gross rating points by generating a composite polarization probability for the first polarized media property based on the first polarization probability and the second polarization probability and determining the number of impressions to achieve the desired gross rating points based on the composite polarization probability for the first polarized media property.

21. The system of claim 13, further comprising instructions that, when executed by the at least one processor, cause the system to:

determine a cost per polarization probability percentage for each polarized media property in the database of polarized media properties based on the polarization probabilities for each polarized media property; and

select a set of targeted polarized media properties to include in the online ad campaign based on the determined cost per polarization probability percentage for each polarized media property.

22. The system of claim 21, further comprising instructions that, when executed by the at least one processor, cause the system to:

determine an available targeted inventory for the selected set of targeted polarized media properties;

determine, by aggregating the available targeted inventory, that the available targeted inventory will achieve the desired gross rating points; and

in response to determining that the available targeted inventory will achieve the desired gross rating points, generating a gross rating points quote based on the selected set of targeted polarized media properties.

23. The system of claim 21, further comprising instructions that, when executed by the at least one processor, cause the system to:

determine an available targeted inventory for the selected set of targeted polarized media properties;

determine, by aggregating the available targeted inventory, that the aggregated available targeted inventory will not achieve the desired gross rating points;

in response to determining that the aggregated available targeted inventory will not achieve the desired gross rating points, select at least one more polarized media property to add to the selected set of targeted polarized media properties;

determine a revised aggregated available targeted inventory based on the selected set of targeted polarized media properties, including the at least one more polarized media property;

determine that the revised aggregated available targeted inventory achieves the desired gross rating points; and

in response to determining that the revised aggregated available targeted inventory achieves the desired gross rating points, generating a gross rating points quote.