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 is prohibited. 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, where conversion events have been excluded from the history. Advertising content is sent to the targetable browser according to a result of applying the model.
1. A computer-implemented method comprising:
by a modeling module:
receiving a respective history of each of a plurality of browsers, each history comprising a first plurality of media consumption events and a corresponding label;
generating a privatized modeling history corresponding to each respective history of each of the plurality of browsers by removing each of the corresponding labels;
determining a first frequency of each of a second plurality of media consumption events among a first plurality of privatized modeling histories and a second frequency of each of the second plurality of media consumption events among a second plurality of privatized modeling histories, wherein each of the first plurality of privatized modeling histories comprise a specific conversion event and wherein each of the second plurality of privatized modeling histories do not comprise the specific conversion event;
building a model based on the first frequency and the second frequency; and
sending the model to a targeting module;
by the targeting module:
receiving, from the modeling module, the model;
receiving, from a real-time bidding exchange, a history of a targetable browser comprising a third plurality of media consumption events; and
responsive to receiving the history of a targetable browser:
generating a privatized targeting history of the targetable browser by removing a specific media consumption event from the history of the targetable browser;
applying the model to the privatized targeting history of the targetable browser; and
sending a response to the real-time bidding exchange according to a result of applying the model.
2. The method of claim 1 , wherein the corresponding label comprises a cookie.
3. The method of claim 1 , wherein the corresponding label comprises personally identifiable information.
4. The method of claim 1 , wherein removing each of the corresponding labels comprises performing a one-way hash of each of the corresponding labels to generate a corresponding hashed label.
5. The method of claim 1 , wherein the specific media consumption event is a conversion event.
6. The method of claim 1 , further comprising, by the targeting model, receiving a description of the specific media consumption event.
7. The method of claim 6 , further comprising receiving the description of the specific media consumption event from one of the modeling module, a configuration system, and an advertiser.
8. The method of claim 1 , wherein sending the response to the real-time bidding exchange according to the result of applying the model comprises one of setting a bid price, deciding to bid, applying a frequency cap, selecting a supplemental content creative, customizing a supplemental content.
9. The method of claim 1 , wherein receiving the history of the targetable browser further comprises receiving an expiration time from the real-time bidding system, and wherein sending the response further comprises sending the response before the expiration time.
10. The method of claim 1 , wherein:
the modeling module operates according to a policy which requires disabling targeting, based on the corresponding label, of every browser of the plurality of browsers; and
the targeting module operates according to a policy which requires preventing targeting of a specific browser based on a presence of the specific media consumption event in a corresponding browser history of the specific browser.
11. A non-transitory computer-readable storage medium storing processor-executable computer program instructions that, when executed, cause a computer processor to perform a method, the method comprising:
by a modeling module:
receiving a respective history of each of a plurality of browsers, each history comprising a first plurality of media consumption events and a corresponding label;
generating a privatized modeling history corresponding to each respective history of each of the plurality of browsers by removing each of the corresponding labels;
determining a first frequency of each of a second plurality of media consumption events among a first plurality of privatized modeling histories and a second frequency of each of the second plurality of media consumption events among a second plurality of privatized modeling histories, wherein each of the first plurality of privatized modeling histories comprise a specific conversion event and wherein each of the second plurality of privatized modeling histories do not comprise the specific conversion event;
building a model based on the first frequency and the second frequency; and
sending the model to a targeting module;
by the targeting module:
receiving, from the modeling module, the model;
receiving, from a real-time bidding exchange, a history of a targetable browser comprising a third plurality of media consumption events; and
responsive to receiving the history of a targetable browser:
generating a privatized targeting history of the targetable browser by removing a specific media consumption event from the history of the targetable browser;
applying the model to the privatized targeting history of the targetable browser; and
sending a response to the real-time bidding exchange according to a result of applying the model.
12. The medium of claim 11 , wherein the corresponding label comprises a cookie.
13. The medium of claim 11 , wherein the corresponding label comprises personally identifiable information.
14. The medium of claim 11 , wherein removing each of the corresponding labels comprises performing a one-way hash of each of the corresponding labels to generate a corresponding hashed label.
15. The medium of claim 11 , wherein the specific media consumption event is a conversion event.
16. The medium of claim 11 , wherein the method further comprises, by the targeting model, receiving a description of the specific media consumption event.
17. The medium of claim 16 , wherein the method further comprises receiving the description of the specific media consumption event from one of the modeling module, a configuration system, and an advertiser.
18. The medium of claim 11 , wherein sending the response to the real-time bidding exchange according to the result of applying the model comprises one of setting a bid price, deciding to bid, applying a frequency cap, selecting a supplemental content creative, customizing a supplemental content.
19. The medium of claim 11 , wherein receiving the history of the targetable browser further comprises receiving an expiration time from the real-time bidding system, and wherein sending the response further comprises sending the response before the expiration time.
20. The medium of claim 11 , wherein:
the modeling module operates according to a policy which requires disabling targeting, based on the corresponding label, of every browser of the plurality of browsers; and
the targeting module operates according to a policy which requires preventing targeting of a specific browser based on a presence of the specific media consumption event in a corresponding browser history of the specific browser.
21. A system comprising:
a processor; and
a non-transitory computer-readable storage medium storing processor-executable computer program instructions that, when executed, cause a computer processor to perform a method, the method comprising:
by a modeling module:
receiving a respective history of each of a plurality of browsers, each history comprising a first plurality of media consumption events and a corresponding label;
generating a privatized modeling history corresponding to each respective history of each of the plurality of browsers by removing each of the corresponding labels;
determining a first frequency of each of a second plurality of media consumption events among a first plurality of privatized modeling histories and a second frequency of each of the second plurality of media consumption events among a second plurality of privatized modeling histories, wherein each of the first plurality of privatized modeling histories comprise a specific conversion event and wherein each of the second plurality of privatized modeling histories do not comprise the specific conversion event;
building a model based on the first frequency and the second frequency; and
sending the model to a targeting module;
by the targeting module:
receiving, from the modeling module, the model;
receiving, from a real-time bidding exchange, a history of a targetable browser comprising a third plurality of media consumption events; and
responsive to receiving the history of a targetable browser:
generating a privatized targeting history of the targetable browser by removing a specific media consumption event from the history of the targetable browser;
applying the model to the privatized targeting history of the targetable browser; and
sending a response to the real-time bidding exchange according to a result of applying the model.
22. The system of claim 21 , wherein the corresponding label comprises a cookie.
23. The system of claim 21 , wherein the corresponding label comprises personally identifiable information.
24. The system of claim 21 , wherein removing each of the corresponding labels comprises performing a one-way hash of each of the corresponding labels to generate a corresponding hashed label.
25. The system of claim 21 , wherein the specific media consumption event is a conversion event.
26. The system of claim 21 , wherein the method further comprises, by the targeting model, receiving a description of the specific media consumption event.
27. The system of claim 26 , wherein the method further comprises receiving the description of the specific media consumption event from one of the modeling module, a configuration system, and an advertiser.
28. The system of claim 21 , wherein sending the response to the real-time bidding exchange according to the result of applying the model comprises one of setting a bid price, deciding to bid, applying a frequency cap, selecting a supplemental content creative, customizing a supplemental content.
29. The system of claim 21 , wherein receiving the history of the targetable browser further comprises receiving an expiration time from the real-time bidding system, and wherein sending the response further comprises sending the response before the expiration time.
30. The system of claim 21 , wherein:
the modeling module operates according to a policy which requires disabling targeting, based on the corresponding label, of every browser of the plurality of browsers; and
the targeting module operates according to a policy which requires preventing targeting of a specific browser based on a presence of the specific media consumption event in a corresponding browser history of the specific browser.