Protected audience selection
Protected audience selection system. Media consumption histories of browsers which have converted are received at a modeling system where targeting of browsers has been disabled by excluding targeting labels. A model is built by determining a frequency of each respective media consumption event among the histories and comparing each determined frequency of a respective media consumption event to a frequency of the respective media consumption event among a population of browsers without the conversion event. The model is sent to a targeting system which excludes conversion events. A description of the conversion event is received at the targeting system. A history of a targetable browser is received at the targeting system. The model is applied to the history of the targetable browser at the targeting system in the absence of records of conversion events. Advertising content is sent to the targetable browser according to a result of applying the model.
1. A computer-implemented method comprising:
receiving, at a modeling system, a respective history of each of a plurality of browsers, each history comprising a plurality of media consumption events and a conversion event;
disabling targeting of browsers from the modeling system according to a modeling system data policy which excludes targeting labels from the modeling system, by removing targeting labels from the histories before storing the histories in a storage;
building a model, by the modeling system, comprising:
determining a frequency of each respective media consumption event among the histories in the storage; and
comparing each determined frequency of a respective media consumption event to a frequency of the respective media consumption event among a population of browsers without the conversion event;
sending the model to a targeting system, the targeting system having a data policy which excludes conversion events from the targeting system;
receiving, at the targeting system, a description of the conversion event;
receiving, at the targeting system, a history of a targetable browser;
purging all conversion events from the history of the targetable browser according to the data policy of the targeting system;
applying the model to the purged history of the targetable browser at the targeting system; and
sending advertising content to the targetable browser according to a result of applying the model.
2. The method of claim 1 , further comprising:
receiving a bid request from a real time bidding exchange, the bid request comprising a notification of an opportunity to expose the targetable browser to advertising content;
and wherein:
applying the model is responsive to receiving the bid request.
3. The method of claim 2 , wherein sending advertising content comprises:
configuring a bid response with respect to the bid request according to a result of applying the model before the bid request expires.
4. The method of claim 1 , wherein:
the conversion model is generated without the specified browser's history.
5. The method of claim 1 , further comprising:
presenting a graphical user interface to a user, the graphical user interface comprising a user control for setting a threshold for the result of applying the model; and
receiving the threshold set by the user through the graphical user interface.
6. The method of claim 5 , wherein sending comprises:
sending advertising content to the targetable browser if the result of applying the model satisfies the threshold.
7. The method of claim 1 , wherein sending advertising content comprises:
selecting advertising content according to a result of applying the model.
8. The method of claim 1 , wherein sending advertising content comprises:
customizing advertising content according to a result of applying the model.
9. The method of claim 1 , wherein:
the data policy of the modeling system excludes personally identifiable information from the modeling system.
10. The method of claim 1 , wherein:
the targeting label comprises a cookie.
11. The method of claim 1 , further comprising:
the targeting label comprises a cookie set by the targeting system.
12. A non-transitory computer-readable storage medium executing computer program instructions for operating an advertising campaign, the computer program instructions comprising instructions for:
receiving, at a modeling system, a respective history of each of a plurality of browsers, each history comprising a plurality of media consumption events and a conversion event;
disabling targeting of browsers from the modeling system according to a modeling system data policy which excludes targeting labels from the modeling system, by removing targeting labels from the histories before storing the histories in a storage;
building a model, by the modeling system, comprising:
determining a frequency of each respective media consumption event among the histories in the storage; and
comparing each determined frequency of a respective media consumption event to a frequency of the respective media consumption event among a population of browsers without the conversion event;
sending the model to a targeting system, the targeting system having a data policy which excludes conversion events from the targeting system;
receiving, at the targeting system, a description of the conversion event;
receiving, at the targeting system, a history of a targetable browser;
purging all conversion events from the history of the targetable browser according to the data policy of the targeting system;
applying the model to the purged history of the targetable browser at the targeting system; and
sending advertising content to the targetable browser according to a result of applying the model.
13. The medium of claim 12 , wherein sending advertising content comprises:
receiving a bid request from a real time bidding exchange, the bid request comprising a notification of an opportunity to expose the targetable browser to advertising content;
and wherein:
applying the model is responsive to receiving the bid request.
14. The medium of claim 13 , wherein sending advertising content comprises:
configuring a bid response with respect to the bid request according to a result of applying the model before the bid request expires.
15. The medium of claim 12 , wherein the medium further comprises instructions for:
presenting a graphical user interface to a user, the graphical user interface comprising a user control for setting a threshold for the result of applying the model; and
receiving the threshold set by the user through the graphical user interface.
16. The medium of claim 12 , wherein sending comprises:
sending advertising content to the targetable browser if the result of applying the model satisfies the threshold.
17. A system comprising:
a processor;
a computer-readable storage medium storing processor-executable computer program instructions for operating an advertising campaign, the instructions comprising instructions for:
receiving, at a modeling module, a respective history of each of a plurality of browsers, each history comprising a plurality of media consumption events and a conversion event;
disabling targeting of browsers from the modeling module according to a modeling module data policy which excludes targeting labels from the modeling module, by removing targeting labels from the histories before storing the histories in a modeling module storage;
building a model, at the modeling module, comprising:
determining a frequency of each respective media consumption event among the histories in the modeling module storage; and
comparing each determined frequency of a respective media consumption event to a frequency of the respective media consumption event among a population of browsers without the conversion event;
sending the model to a targeting module, the targeting module having a data policy which excludes conversion events from the targeting module;
receiving, at the targeting module, a description of the conversion event;
receiving, at the targeting module, a history of a targetable browser;
purging all conversion events from the history of the targetable browser according to the data policy of the targeting module,
applying the model to the purged history of the targetable browser at the targeting module; and
sending advertising content to the targetable browser according to a result of applying the model.
18. The system of claim 17 , wherein sending advertising content comprises:
receiving a bid request from a real time bidding exchange, the bid request comprising a notification of an opportunity to expose the targetable browser to advertising content;
and wherein:
applying the model is responsive to receiving the bid request.
19. The system of claim 17 , wherein sending advertising content comprises:
configuring a bid response to the targetable browser according to a result of applying the model before the bid request expires.
20. The system of claim 17 , wherein the instructions further comprises instructions for: presenting a graphical user interface to a user, the graphical user interface comprising a user control for setting a threshold for the result of applying the model; and receiving the threshold set by the user through the graphical user interface; and wherein sending comprises: sending advertising content to the targetable browser if the result of applying the model satisfies the threshold.