Real-time bidding through placebo-based experimentation
Systems and methods for operating placebo-based experiments are described for online advertisements. One or more embodiments of the disclosed systems and methods utilizes an ad swapping approach to offer placebo media exposures, at no additional cost to an advertiser. One or more embodiments further provide a native experimentation platform that allows users to run tests of ad placements to measure the effectiveness of ads and view results displayed on a user interface. The disclosed systems and methods can assign viewers into a test group if shown the test ad or a control group if shown a control ad. The control ad can be provided at no cost to the advertiser for embodiments where the placebo ad belongs to an alternative advertiser. Effectiveness of third party attribution can also be evaluated. The disclosed systems and methods can define experiment parameters, including control frequency, test viewer groups, and control viewer groups.
1. In a digital medium environment for real-time bidding on impression opportunities associated with viewers simultaneously accessing digital content, a computer-implemented method of conducting a placebo-based experiment for improving online campaigns, comprising:
identifying a first set of campaign parameters of a first advertiser and a second set of campaign parameters of a second advertiser;
running a media lift experiment for the first advertiser by:
receiving, from a remote server, a bid request package for an impression opportunity associated with a first viewer visiting a website;
determining, by at least one processor, that the first viewer corresponds to a control group; and
based on the first set of campaign parameters, the second set of campaign parameters, and the determination that the first viewer corresponds to the control group, automatically responding, by the at least one processor, to the bid request package by sending a control ad associated with the second advertiser to the remote server for display to a client device of the first viewer via the website;
placing instructions in the control ad associated with the second advertiser that cause a first tracking cookie corresponding to the first advertiser to be transmitted to the client device of the first viewer when the control ad is presented on the client device, wherein the first tracking cookie references a test ad associated with the first advertiser;
determining one or more conversion events corresponding to the control ad associated with the second advertiser based on the first tracking cookie corresponding to the first advertiser; and
determining a measure of media lift for the test ad associated with the first advertiser based at least in part on subtracting the one or more conversion events corresponding to the control ad associated with the second advertiser and the first tracking cookie from test conversion events corresponding to the test ad associated with the first advertiser.
2. The method of claim 1 , wherein automatically responding to the bid request package comprises sending a bid for the control ad associated with the second advertiser to the remote server within 250 milliseconds of receiving the bid request package from the remote server.
3. The method of claim 1 , further comprising providing the measure of media lift for display via a user interface of a client device, wherein the user interface comprises a selectable element for modifying the control ad.
4. The method of claim 3 , wherein the user interface further comprises selectable elements for modifying the first set of campaign parameters.
5. The method of claim 1 , wherein running the media lift experiment for the first advertiser further comprises:
determining that the first viewer satisfies both the first set of campaign parameters of the first advertiser and the second set of campaign parameters of the second advertiser; and
automatically responding to the bid request package by sending the control ad associated with the second advertiser based on the determination that the first viewer satisfies both the first set of campaign parameters and the second set of campaign parameters.
6. The method of claim 1 , further comprising:
receiving, from the remote server, a second bid request package for a second impression opportunity associated with a second viewer;
determining that the second viewer corresponds to a test group; and
based on the first set of campaign parameters and the determination that the first viewer corresponds to the test group, automatically responding to the second bid request package by sending the test ad associated with the first advertiser to the remote server for display to the second viewer.
7. The method of claim 6 , wherein determining the measure of media lift comprises:
identifying a first user interaction by the first viewer with the control ad associated with the second advertiser;
identifying a second user interaction by the second viewer with the test ad associated with the first advertiser; and
comparing the first user interaction by the first viewer with the control ad associated with the second advertiser with the second user interaction by the second viewer with the test ad associated with the first advertiser.
8. The method of claim 7 , wherein:
determining that the first viewer corresponds to the control group comprises assigning the first viewer to the control group by applying a randomizing operation and control frequency threshold value; and
determining that the second viewer corresponds to the test group comprises assigning the second viewer to the test group by applying the randomizing operation and the control frequency threshold value.
9. A system comprising:
at least one server; and
at least one non-transitory computer readable storage medium storing instructions that, when executed by the at least one server, cause the system to:
identify a first set of targeting parameters of a first advertiser and a second set of targeting parameters of a second advertiser;
based on a determination that a first viewer satisfies the first set of targeting parameters and the second set of targeting parameters and based on a determination that the first viewer corresponds to a control group, automatically sending a control ad associated with the second advertiser for display to a client device of the first viewer;
placing instructions in the control ad associated with the second advertiser that cause a first tracking cookie corresponding to the first advertiser to be transmitted to the client device of the first viewer when the control ad is presented on the client device, wherein the first tracking cookie references a test ad associated with the first advertiser;
determining one or more conversion events corresponding to the control ad associated with the second advertiser based on the first tracking cookie corresponding to the first advertiser; and
determining a measure of media lift for the test ad associated with the first advertiser based at least in part on subtracting the one or more conversion events corresponding to the control ad associated with the second advertiser and the first tracking cookie from test conversion events corresponding to the test ad associated with the first advertiser.
10. The system of claim 9 , wherein automatically sending the control ad comprises automatically sending a bid for the control ad associated with the second advertiser within 250 milliseconds of receiving a bid request package.
11. The system of claim 9 , further comprising instructions that, when executed by the at least one server, cause the system to: provide the measure of media lift for display via a user interface of a client device, wherein the user interface comprises a selectable element for modifying the control ad.
12. The system of claim 9 , further comprising instructions that, when executed by the at least one server, cause the system to:
receive a bid request package for an impression opportunity associated with a second viewer;
determine that the second viewer corresponds to a test group; and
based on the first set of targeting parameters and the determination that the first viewer corresponds to the test group, automatically responding to the bid request package by sending the test ad associated with the first advertiser for display to the second viewer.
13. The system of claim 12 , further comprising instructions that, when executed by the at least one server, cause the system to determine the measure of media lift by:
identifying a first user interaction by the first viewer with the control ad associated with the second advertiser;
identifying a second user interaction by the second viewer with the test ad associated with the first advertiser; and
comparing the first user interaction by the first viewer with the control ad associated with the second advertiser with the second user interaction by the second viewer with the test ad associated with the first advertiser.
14. A non-transitory computer readable medium storing instructions thereon that, when executed by at least one processor, cause a computing device to:
identify a first set of campaign parameters of a first advertiser and a second set of campaign parameters of a second advertiser;
run a media lift experiment for the first advertiser by:
receiving, from a remote server, a bid request package for an impression opportunity associated with a first viewer visiting a website;
determining, by the at least one processor, that the first viewer corresponds to a control group; and
based on the first set of campaign parameters, the second set of campaign parameters, and the determination that the first viewer corresponds to the control group, automatically responding, by the at least one processor, to the bid request package by sending a control ad associated with the second advertiser to the remote server for display to a client device of the first viewer via the website;
placing instructions in the control ad associated with the second advertiser that cause a first tracking cookie corresponding to the first advertiser to be transmitted to the client device of the first viewer when the control ad is presented on the client device, wherein the first tracking cookie references a test ad associated with the first advertiser;
determining one or more conversion events corresponding to the control ad associated with the second advertiser based on the first tracking cookie corresponding to the first advertiser; and
determining a measure of media lift for the test ad associated with the first advertiser based at least in part on subtracting the one or more conversion events corresponding to the control ad associated with the second advertiser and the first tracking cookie from test conversion events corresponding to the test ad associated with the first advertiser.
15. The non-transitory computer readable medium of claim 14 , wherein automatically responding to the bid request package comprises sending a bid for the control ad associated with the second advertiser to the remote server within 250 milliseconds of receiving the bid request package from the remote server.
16. The non-transitory computer readable medium of claim 14 , wherein running the media lift experiment for the first advertiser further comprises:
determining that the first viewer satisfies both the first set of campaign parameters of the first advertiser and the second set of campaign parameters of the second advertiser; and
automatically responding to the bid request package by sending the control ad associated with the second advertiser based on the determination that the first viewer satisfies both the first set of campaign parameters and the second set of campaign parameters.
17. The non-transitory computer readable medium of claim 14 , further comprising instructions stored thereon that, when executed by the at least one processor, cause the computing device to:
receive, from the remote server, a second bid request package for a second impression opportunity associated with a second viewer;
determine that the second viewer corresponds to a test group; and
based on the first set of campaign parameters and the determination that the first viewer corresponds to the test group, automatically respond to the second bid request package by sending the test ad associated with the first advertiser to the remote server for display to the second viewer.
18. The non-transitory computer readable medium of claim 17 , wherein determining the measure of media lift comprises:
identifying a first user interaction by the first viewer with the control ad associated with the second advertiser;
identifying a second user interaction by the second viewer with the test ad associated with the first advertiser; and
comparing the first user interaction by the first viewer with the control ad associated with the second advertiser with the second user interaction by the second viewer with the test ad associated with the first advertiser.
19. The non-transitory computer readable medium of claim 18 , wherein:
determining that the first viewer corresponds to the control group comprises assigning the first viewer to the control group by applying a randomizing operation and control frequency threshold value; and
determining that the second viewer corresponds to the test group comprises assigning the second viewer to the test group by applying the randomizing operation and the control frequency threshold value.
20. The non-transitory computer readable medium of claim 14 , further comprising instructions stored thereon that, when executed by the at least one processor, cause the computing device to provide the measure of media lift for display via a user interface of a client device, wherein the user interface comprises a selectable element for modifying the control ad.