Using proxy behaviors for audience selection
Method and system for assessing the suitability of an entity using a proxy. A description of a behavior associated with a desirable audience is received. A proxy behavior estimated to be characteristic of the desirable audience is selected. The proxy behavior comprises the performance of proxy events related to the consumption of media received by an entity over a network, which can be found in an entity's consumption history. An entity can be assessed for inclusion in a proxy audience, by examining the entity's consumption history for proxy behaviors. A behavioral model is built using a training set comprising the proxy audience. By applying the behavioral model to the consumption history of a specified entity, the specified entity's suitability for selection can be determined. Advantageously, in an embodiment, the invention enables the use of behavioral modeling techniques even when the complete behavior of the desirable audience is not available.
1. A computer-implemented method comprising:
receiving at least one focus keyword search string;
accessing a respective consumption history of each of a plurality of web browser instances;
examining the respective consumption history of each of the plurality of web browser instances for at least one proxy event, wherein each proxy event comprises a keyword search corresponding to at least one of the received at least one focus keyword search strings;
selecting a training set of web browser instances comprising:
identifying a set of proxy web browser instances from the plurality of web browser instances, each proxy web browser instance having one or more proxy events in each proxy web browser instance's respective consumption history;
assigning a proxy event weight to each proxy event in each proxy web browser instance's respective consumption history; and
selecting the training set of web browser instances from the set of proxy web browser instances based on the proxy event weight of the one or more proxy events in each proxy web browser instance's respective consumption history;
building a behavioral model based on the training set of web browser instances;
receiving a specified web browser instance's consumption history;
assessing a suitability of the specified web browser instance for receipt of an advertising content by applying the behavioral model to the specified web browser instance's consumption history; and
based on a result of the assessing, sending instructions to a content provider to provide the advertising content to the specified web browser instance.
2. The method of claim 1 , wherein:
the proxy event weight assigned to each proxy event in each proxy web browser instance's respective consumption history corresponds to a recency of the proxy event in each web browser instance's respective consumption history.
3. The method of claim 1 , wherein:
the proxy event weight assigned to each proxy event in each proxy web browser instance's respective consumption history corresponds to a frequency of the proxy event in each web browser instance's respective consumption history.
4. The method of claim 1 , wherein:
each focus keyword search string corresponds to a focus parameter, wherein an importance of each focus keyword search string is characterized by the corresponding focus parameter; and
the proxy event weight assigned to each proxy event in each proxy web browser instance's respective consumption history is based on the corresponding focus parameter.
5. The method of claim 4 , wherein:
the focus parameter increases the proxy event weight.
6. The method of claim 4 , wherein:
the focus parameter decreases the proxy event weight.
7. The method of claim 4 , wherein:
the focus parameter comprises a maximum bid.
8. The method of claim 4 , wherein the focus parameter is descriptive of a search engine advertising campaign.
9. The method of claim 1 wherein:
receiving at least one focus keyword search string comprises receiving two or more focus keyword search strings.
10. A non-transitory computer readable storage medium including computer program instructions that when executed, cause a computer processor to perform operations comprising:
receiving at least one focus keyword search string;
accessing a respective consumption history of each of a plurality of web browser instances;
examining the respective consumption history of each of the plurality of web browser instances for at least one proxy event, wherein each proxy event comprises a keyword search corresponding to at least one of the received at least one focus keyword search strings;
selecting a training set of web browser instances comprising:
identifying a set of proxy web browser instances from the plurality of web browser instances, each proxy web browser instance having one or more proxy events in each proxy web browser instance's respective consumption history;
assigning a proxy event weight to each proxy event in each proxy web browser instance's respective consumption history; and
selecting the training set of web browser instances from the set of proxy web browser instances based on the proxy event weight of the one or more proxy events in each proxy web browser instance's respective consumption history;
building a behavioral model based on the training set of web browser instances;
receiving a specified web browser instance's consumption history;
assessing a suitability of the specified web browser instance for receipt of an advertising content by applying the behavioral model to the specified web browser instance's consumption history; and
based on a result of the assessing, sending instructions to a content provider to provide the advertising content to the specified web browser instance.
11. The medium of claim 10 , wherein:
the proxy event weight assigned to each proxy event in each proxy web browser instance's respective consumption history corresponds to a recency of the proxy event in each web browser instance's respective consumption history.
12. The medium of claim 10 , wherein:
the proxy event weight assigned to each proxy event in each proxy web browser instance's respective consumption history corresponds to a frequency of the proxy event in each web browser instance's respective consumption history.
13. The medium of claim 10 , wherein:
each focus keyword search string corresponds to a focus parameter, wherein an importance of each focus keyword search string is characterized by the corresponding focus parameter; and
the proxy event weight assigned to each proxy event in each proxy web browser instance's respective consumption history is based on the corresponding focus parameter.
14. The medium of claim 13 , wherein:
the focus parameter increases the proxy event weight.
15. The medium of claim 13 , wherein:
the focus parameter decreases the proxy event weight.
16. The medium of claim 13 , wherein:
the focus parameter comprises a maximum bid.
17. The medium of claim 13 , wherein the focus parameter is descriptive of a search engine advertising campaign.
18. The medium of claim 10 , wherein:
receiving at least one focus keyword search string comprises receiving two or more focus keyword search strings.
19. A system comprising:
a processor; and
a non-transitory computer readable storage medium including computer program instructions that when executed, cause a computer processor to perform operations comprising:
receiving at least one focus keyword search string;
accessing a respective consumption history of each of a plurality of web browser instances;
examining the respective consumption history of each of the plurality of web browser instances for at least one proxy event, wherein each proxy event comprises a keyword search corresponding to at least one of the received at least one focus keyword search strings;
selecting a training set of web browser instances comprising:
identifying a set of proxy web browser instances from the plurality of web browser instances, each proxy web browser instance having one or more proxy events in each proxy web browser instance's respective consumption history;
assigning a proxy event weight to each proxy event in each proxy web browser instance's respective consumption history; and
selecting the training set of web browser instances from the set of proxy web browser instances based on the proxy event weight of the one or more proxy events in each proxy web browser instance's respective consumption history;
building a behavioral model based on the training set of web browser instances;
receiving a specified web browser instance's consumption history;
assessing a suitability of the specified web browser instance for receipt of an advertising content by applying the behavioral model to the specified web browser instance's consumption history; and
based on a result of the assessing, sending instructions to a content provider to provide the advertising content to the specified web browser instance.
20. The system of claim 19 , wherein:
the proxy event weight assigned to each proxy event in each proxy web browser instance's respective consumption history corresponds to a recency of the proxy event in each web browser instance's respective consumption history.
21. The system of claim 19 , wherein:
proxy event weight assigned to each proxy event in each proxy web browser instance's respective consumption history corresponds to a frequency of the proxy event in each web browser instance's respective consumption history.
22. The system of claim 19 , wherein:
each focus keyword search string corresponds to a focus parameter, wherein an importance of each focus keyword search string is characterized by the corresponding focus parameter; and
the proxy event weight assigned to each proxy event in each proxy web browser instance's respective consumption history is based on the corresponding focus parameter.
23. The system of claim 22 , wherein:
the focus parameter increases the proxy event weight.
24. The system of claim 22 , wherein:
the focus parameter decreases the proxy event weight.
25. The system of claim 22 , wherein:
the focus parameter comprises a maximum bid.
26. The system of claim 22 , wherein the focus parameter is descriptive of a search engine advertising campaign.
27. The system of claim 19 , wherein:
receiving at least one focus keyword search string comprises receiving two or more focus keyword search strings.