SYSTEMS AND METHODS FOR DEFINING VIDEO ADVERTISING CHANNELS
Described are computer-based methods and apparatuses, including computer program products, for defining video advertising channels. A set of requirements is received for an advertising channel. A training set of video content is identified based on the set of requirements. A set of baseline categorizations is received that includes, for each video in the training set of video content, a categorization for each requirement from the set of requirements. A set of experiments is calculated based on the training set of video content and the set of baseline categorizations to determine video content for the advertising channel.
1 . A computerized method for defining an advertising channel, comprising:
receiving, by a computing device, a set of requirements for an advertising channel;
identifying, by the computing device, a training set of video content based on the set of requirements;
receiving, by the computing device, a set of baseline categorizations comprising, for each video in the training set of video content, a categorization for each requirement from the set of requirements; and
calculating, by the computing device, a set of experiments based on the training set of video content and the set of baseline categorizations to determine video content for the advertising channel.
2 . The method of claim 1 , wherein calculating the set of experiments comprises calculating a master set of experiments based on a set of candidate experiments, the training set of video content, and the set of baseline categorizations.
3 . The method of claim 2 , wherein:
each candidate experiment from the set of candidate experiments comprises (a) a set of input parameters and (b) a set of training parameters; and
calculating the master set of experiments comprises executing each candidate experiment using:
one or more different sets of input parameters determined based on the training set of video content; and
one or more different sets of training parameters.
4 . The method of claim 2 , wherein calculating the master set of experiments comprises combining two or more candidate experiments from the set of candidate experiments.
5 . The method of claim 2 , wherein calculating the master set of experiments comprises executing one or more candidate experiments from the set of candidate experiments based on a past execution of the one or more candidate experiments for a second advertising channel.
6 . The method of claim 2 , wherein calculating the set of experiments comprises calculating a classification model based on the master set of experiments, wherein the classification model is used to determine video content for the advertising channel.
7 . The method of claim 6 , wherein calculating the classification model comprises combining one or more experiments from the master set of experiments based on a mathematical analysis of the master set of experiments.
8 . The method of claim 7 , wherein calculating the classification model comprises calculating the classification model based on one or more tradeoffs, including:
a resource utilization required to execute the classification model;
a threshold determined based on an expected number of videos that will be assigned to the advertising channel;
an impact of improper categorization for the advertising channel; or any combination thereof.
9 . The method of claim 1 , further comprising:
generating a set of index data for the training set of video content comprising index data for each video in the training set of video content; and
calculating the set of experiments based on the set of index data.
10 . The method of claim 1 , further comprising generating a web page for each video in the training set of video content, the web page comprising:
a plurality of still images from the video;
a copy of the video; and
the set of requirements for the advertising channel.
11 . The method of claim 1 , further comprising:
executing the set of experiments using the training set of video content to calculate a baseline performance of the set of experiments;
receiving a second training set of video content;
executing the set of experiments using the second training set of video content to identify one or more videos for inclusion with the advertising channel; and
receiving validation information for the identified one or more videos.
12 . The method of claim 1 , wherein identifying the training set of video content based on the set of requirements comprises, for each video from the training set of video content:
retrieving the video from the internet using a keyword search, a user behavior search, a publisher tag search, or any combination thereof; and
storing user experience data indicative of a user's experience of watching the video on the internet.
13 . A system for defining an advertising channel, comprising:
a database; and
a server in communication with the database configured to:
receive a set of requirements for an advertising channel and store the set of requirements in the database;
identify a training set of video content based on the set of requirements and store the training set of video content in the database;
receive, for each video in the training set of video content, a set of baseline categorizations for each requirement from the set of requirements; and
calculate a set of experiments based on the training set of video content and the set of baseline categorizations to determine video content for the advertising channel.
14 . The system of claim 13 , wherein the server is further configured to store each requirement from the set of requirements in the database as a question and an acceptable answer to the question.
15 . The system of claim 13 , wherein the server is further configured to calculate a master set of experiments based on a set of candidate experiments, the training set of video content, and the set of baseline categorizations.
16 . The system of claim 15 , wherein:
each candidate experiment from the set of candidate experiments comprises (a) a set of input parameters and (b) a set of training parameters; and
the server is further configured to calculate the master set of experiments by executing each candidate experiment using:
one or more different sets of input parameters determined based on the training set of video content; and
one or more different sets of training parameters.
17 . The system of claim 15 , wherein the server is further configured to calculate a classification model based on the set of experiments, wherein the classification model is used to determine video content for the advertising channel.
18 . The system of claim 17 , wherein the server is further configured to calculate the classification model by combining one or more experiments from the master set of experiments based on a mathematical analysis of the master set of experiments.
19 . The system of claim 17 , wherein the server is further configured to calculate the classification model based on one or more tradeoffs, including:
a resource utilization required to execute the classification model;
a threshold determined based on an expected number of videos that will be assigned to the advertising channel;
an impact of improper categorization for the advertising channel; or any combination thereof.
20 . A computer program product, tangibly embodied in a non-transitory computer readable medium, the computer program product including instructions being configured to cause a data processing apparatus to:
receive a set of requirements for an advertising channel;
identify a training set of video content based on the set of requirements;
receive a set of baseline categorizations comprising, for each video in the training set of video content, a categorization for each requirement from the set of requirements; and
calculate a set of experiments based on the training set of video content and the set of baseline categorizations to determine video content for the advertising channel.