SYSTEMS AND METHODS FOR BUILDING KEYWORD SEARCHABLE AUDIENCE BASED ON PERFORMANCE RANKING
Systems and methods for building keyword searchable audience based on performance ranking are provided. The system includes a processor and a non-transitory storage medium accessible to the processor. The system includes a memory storing a database comprising segment data and campaign data. A computer server is in communication with the memory and the database, the computer server programmed to: obtain a performance-lift vector for an audience segment; obtain a campaign vector using meta-data from the campaign data; obtain a keyword vector for the audience segment using the performance-lift vector and the campaign vector; receive an input from a user interface accessible to an advertiser; and search the segment data at least partially based on the input and the keyword vector for segments in the segment data.
1 . A system comprising:
a processor and a non-transitory storage medium accessible to the processor;
a memory storing a database comprising segment data and campaign data;
a computer server in communication with the memory and the database, the computer server programmed to:
obtain a performance-lift vector for an audience segment, the performance-lift vector comprising a difference of a performance of the audience segment for a campaign and an average performance of other audience segments for the campaign;
obtain a campaign vector using meta-data from the campaign data;
obtain a keyword vector for the audience segment using the performance-lift vector and the campaign vector;
receive an input from a user interface accessible to an advertiser; and
search the segment data at least partially based on the input and the keyword vector for segments in the segment data.
2 . The system of claim 1 , wherein the database comprises segment data comprising: search data, social data, content data, and email data.
3 . The system of claim 1 , wherein the audience segment comprises a plurality of audience features comprising at least one of: a geographical feature of the audience segment, a demographical feature of the audience segment, a mobile application related to the audience segment, a technology related to the audience segment, and a publisher related to the audience segment.
4 . The system of claim 3 , wherein the user interface comprises a plurality user input fields at least partially related to the plurality of audience features.
5 . The system of claim 1 , wherein the computer server is programmed to obtain and update the performance-lift vector, the campaign vector, and the keyword vector periodically in an offline training process.
6 . The system of claim 1 ,
wherein the computer server is programmed to obtain an input vector using the input, the input vector indicating at least one of: a geographical feature, a demographical feature, a mobile application feature, a technology feature, and a publisher feature; and
wherein the computer server is programmed to select and recommend an audience segment to the advertiser using a dot product of the input vector and the keyword vector.
7 . The system of claim 1 , wherein the campaign vector comprises a sub-vector of keywords and a sub-vector of weighs corresponding to the sub-vector of keywords, and the sub-vector of keywords comprises keywords at least partially related to creative landing uniform resource locator (URL), advertiser name, and product name.
8 . The system of claim 7 , wherein the computer server is programmed to obtain the sub-vector of weighs corresponding to the sub-vector of keywords using a process based on a term frequency-inverse document frequency (TF-IDF) of the keywords in the sub-vector of keywords.
9 . A method, comprising:
obtaining, by one or more devices having a processor, segment data and campaign data from a memory storing a database;
obtaining, by the one or more devices, a performance-lift vector for an audience segment, the performance-lift vector comprising a difference of a performance of the audience segment for a campaign and an average performance of other audience segments for the campaign;
obtaining, by the one or more devices, a campaign vector using meta-data from the campaign data;
obtaining, by the one or more devices, a keyword vector for the audience segment using the performance-lift vector and the campaign vector; and
searching, by the one or more devices, the segment data at least partially based on an input and the keyword vector for segments in the segment data.
10 . The method of claim 9 , further comprising:
receiving the input from a user interface accessible to an advertiser.
11 . The method of claim 10 , wherein the audience segment comprises a plurality of audience features comprising at least one of: a geographical feature of the audience segment, a demographical feature of the audience segment, a mobile application related to the audience segment, a technology related to the audience segment, and a publisher related to the audience segment.
12 . The method of claim 11 , wherein the user interface comprises a plurality user input fields at least partially related to the plurality of audience features.
13 . The method of claim 9 , further comprising:
obtaining and updating the performance-lift vector, the campaign vector, and the keyword vector periodically in an offline training process.
14 . The method of claim 9 , further comprising:
obtaining an input vector using the input, the input vector indicating at least one of: a geographical feature, a demographical feature, a mobile application feature, a technology feature, and a publisher feature;
selecting an audience segment using a dot product of an input vector and the keyword vector; and
displaying the selected audience segment in a user interface accessible to an advertiser.
15 . The method of claim 9 , wherein the campaign vector comprises a sub-vector of keywords and a sub-vector of weighs corresponding to the sub-vector of keywords, and the sub-vector of keywords comprises keywords at least partially related to creative landing uniform resource locator (URL), advertiser name, and product name.
16 . The method of claim 15 , further comprising:
obtaining the sub-vector of weighs corresponding to the sub-vector of keywords using a process based on a term frequency-inverse document frequency (TF-IDF) of the keywords in the sub-vector of keywords.
17 . A non-transitory storage medium configured to store modules comprising:
module for obtaining a performance-lift vector for an audience segment, the performance-lift vector comprising a difference of a performance of the audience segment for a campaign and an average performance of other audience segments for the campaign;
module for obtaining a campaign vector using meta-data from a database comprising campaign data;
module for obtaining a keyword vector for the audience segment using the performance-lift vector and the campaign vector;
module for displaying a user interface and receiving an input from the user interface accessible to an advertiser; and
module for searching a database comprising segment data at least partially based on an input and the keyword vector for segments in the segment data.
18 . The non-transitory storage medium of claim 17 , wherein the modules further comprise:
module for obtaining and updating the performance-lift vector, the campaign vector, and the keyword vector periodically in an offline training process;
module for selecting an audience segment using a dot product of an input vector and the keyword vector, the input vector at least partially related to the input; and
module for displaying the selected audience segment in the user interface.
19 . The non-transitory storage medium of claim 17 ,
wherein the audience segment comprises a plurality of audience features comprising at least one of: a geographical feature of the audience segment, a demographical feature of the audience segment, a mobile application related to the audience segment, a technology related to the audience segment, and a publisher related to the audience segment; and
wherein the user interface comprises a plurality user input fields at least partially related to the plurality of audience features.
20 . The non-transitory storage medium of claim 17 , wherein the campaign vector comprises a sub-vector of keywords and a sub-vector of weighs corresponding to the sub-vector of keywords, and the sub-vector of keywords comprises keywords at least partially related to creative landing uniform resource locator (URL), advertiser name, and product name.
21 . A system for identifying an audience, the system comprising:
a backend computer server in communication with a database, the backend computer server programmed to: obtain a performance-lift vector for an audience segment, obtain a keyword vector for the audience segment at least partially based on the performance-lift vector, and save the keyword vector in the database; and
a frontend computer server in communication with the database, the frontend computer server programmed to: receive an input from a user interface and search the database at least partially based on the input and the keyword vector.
22 . The system of claim 21 , wherein the performance-lift vector comprises a difference of a performance of the audience segment for a campaign and an average performance of other audience segments for the campaign.
23 . The system of claim 21 , wherein the audience segment comprises a plurality of audience features comprising at least one of: a geographical feature of the audience segment, a demographical feature of the audience segment, a mobile application related to the audience segment, a technology related to the audience segment, and a publisher related to the audience segment.
24 . The system of claim 21 , wherein the keyword vector comprises: a plurality of campaign topics indicating semantics relevance and corresponding weights indicating performances of the plurality of campaign topics.
25 . The system of claim 21 , wherein the frontend computer server is programmed to:
obtain an input vector using the input, the input vector indicating at least one of: a geographical feature, a demographical feature, a mobile application feature, a technology feature, and a publisher feature;
select an audience segment using a dot product of the input vector and the keyword vector in real time; and
display information indicating the selected audience to an advertiser.
26 . The system of claim 21 , wherein the backend computer server is programmed to obtain a campaign vector that comprises a sub-vector of keywords and a sub-vector of weighs corresponding to the sub-vector of keywords, and the sub-vector of keywords comprises keywords at least partially related to creative landing uniform resource locator (URL), advertiser name, and product name.
27 . The system of claim 26 , wherein the backend computer server is programmed to obtain and update the performance-lift vector, the campaign vector, and the keyword vector periodically in an offline training process.
28 . The system of claim 27 , wherein the backend computer server is programmed to obtain the sub-vector of weighs corresponding to the sub-vector of keywords using a process based on a term frequency-inverse document frequency (TF-IDF) of the keywords in the sub-vector of keywords.