Methods and systems for modeling campaign goal adjustment

Abstract

A bid determination platform receives specifications for advertisements, each associated with a model configured to adjust a parameter value of a bid based on different combinations of user and/or media content characteristics associated with different advertisement requests. The platform also receives an advertisement request for placement of an advertisement on an advertisement space of a publisher's media content that has been requested by a user, and the advertisement request is associated with a set of user and media content profile data. For each of the advertisements, all or a subset of the set of user and/or media content profile data is input to each model so as to determine an associated parameter value. Bids for each advertisement are determined, with at least some bids being based on the associated parameter value. An optimum bid is sent with a location of its advertisement to the advertisement request sender.

What is claimed is: 
     
         1 . A method for bidding on placement of an advertisement within media content that is deliverable within a computer networking environment, the method comprising:
 at a bid determination platform, receiving specifications for a plurality of first advertisements that are each associated with a model configured to adjust a parameter value of a bid based on a plurality of different combinations of user characteristics and/or media content characteristics associated with different advertisement requests and/or advertisement characteristics associated with different advertisements;   at the bid determination platform, receiving a first advertisement request for bidding for placement of an advertisement on a first advertisement space that is within a first publisher's media content that has been requested by a first user, and the first advertisement request is associated with a first set of user characteristics profile data and media content characteristics profile data;   for the first advertisement request and each of the first advertisements, inputting all or a subset of the first set of user characteristics profile data and/or media content characteristics profile data and/or advertisement characteristics data associated with such each first advertisement to each of the models so as to determine an associated parameter value;   determining a plurality of bids for placement of the plurality of first advertisements on the first advertisement space, wherein at least a first portion of the bids are determined based on the associated parameter values; and   selecting an optimum one of the determined bids and sending the optimum bid, along with a reference to the optimum bid's associated advertisement, from the bid determination platform to a sender of the first advertisement request.   
     
     
         2 . The method of  claim 1 , wherein the first advertisement request is received through a bid exchange system from the first publisher, and the optimum bid is sent to the first publisher via the bid exchange system if the optimum bid is a winning bid for finalizing purchase of placement of the associated first advertisement on a first advertisement space. 
     
     
         3 . The method of  claim 1 , further comprising:
 at the bid determination platform, receiving specifications for a plurality of second advertisements that are each associated with a constant bid goal value and a plurality of constraints; and   for the first advertisement request, filtering the second advertisements based on whether the first set of user profile and media content characteristics profile data and/or advertisement characteristics data associated with such each second advertisement meet each of the second advertisement's constraints,   wherein determination of a second portion of the plurality of bids is based on the constant goal values of the filtered second advertisements.   
     
     
         4 . The method of  claim 1 , wherein the received specifications of the first advertisements are each further associated with a plurality of constraints, the method further comprising filtering the first advertisements based on whether the first set of user characteristics profile data and/or media content characteristics profile data and/or advertisement characteristics data associated with such each first advertisement meet each of the first advertisement's constraints, wherein the first portion of bids are only determined for the filtered first advertisements. 
     
     
         5 . The method of  claim 1 , wherein the models are each configured for real-time computation of a different parameter value, which corresponds to a different bid goal value, for each individual impression and its associated user characteristics profile data and/or media content characteristics profile data that is associated with such each individual's a bid request. 
     
     
         6 . The method of  claim 5 , wherein each first advertisement is further associated with a base bid goal value that is scaled by an output from the associated model. 
     
     
         7 . The method of  claim 5 , wherein the bid goal value of each model that is computed for each impression is equal to a cost per action (CPA) value. 
     
     
         8 . The method of  claim 5 , wherein the bid goal value of each model that is computed for each impression is equal to a cost per click (CPC) value. 
     
     
         9 . The method of  claim 5 , wherein the bid goal value of each model that is computed for each impression is equal to a cost per million impressions (CPM) value. 
     
     
         10 . The method of  claim 5 , wherein the specifications for the plurality of first advertisements are received by:
 at the bid determination platform, receiving a plurality of model files from a plurality of first advertisers or a plurality of model builders, wherein the model files are in a predictive modeling markup language (PMML) format and describe the models;   at the bid determination platform, receiving campaign specifications from at least some of the plurality of first advertisers and/or model builders, wherein each received campaign specification attaches a specific one of the first advertisements to an associated one of the model files; and   deploying each model by converting each model file into a corresponding executable model for use in determining a bid for the corresponding, attached first advertisement if such model file and executable model passes a set of predefined criteria.   
     
     
         11 . The method of  claim 10 , wherein the predefined criteria include a requirement that each model file only use a predefined set of variables as input for its described model. 
     
     
         12 . The method of  claim 10 , wherein at least one of the deployed models is specified as sharable and attached to different first advertisements in different campaign specifications from different advertisers. 
     
     
         13 . The method of  claim 12 , wherein a first one of the deployed models is sold to a particular one of the first advertisers or model builders who was not involved with creating a model file for generating such sold first deployed model. 
     
     
         14 . The method of  claim 5 , wherein at least one of the models is configured for real-time computation of a different parameter value for different user characteristics, which include age, gender, and location of the corresponding user. 
     
     
         15 . The method of  claim 14 , wherein the location of the corresponding user includes a state and direct marketing area (DMA). 
     
     
         16 . The method of  claim 1 , wherein at least one of the models is configured to determine a probability of a user action with respect to an advertisement. 
     
     
         17 . The method of  claim 1 , wherein at least one of the models is configured to adjust a parameter value of a bid based on a plurality of different combinations of user characteristics associated with different advertisement requests. 
     
     
         18 . The method of  claim 17 , wherein the different combinations of user characteristics include different combinations of user demographics and different other contextual factors that affect user behavior differently. 
     
     
         19 . The method of  claim 1 , wherein at least some of the models are configured to adjust a parameter value of a bid based on different combinations of user characteristics and media content characteristics. 
     
     
         20 . The method of  claim 1 , wherein at least one of the models is configured to adjust a parameter value of a bid based on different combinations of user characteristics, media content characteristics, and advertisement characteristics. 
     
     
         21 . The method of  claim 1 , further comprising:
 at the bid determination platform, receiving a plurality of models from a plurality of first advertisers or a plurality of model builders,   wherein receiving the specifications for the first advertisements comprises at least some of the first advertisers associating specific ones of the first advertisements with specific ones of the received models.   
     
     
         22 . A system for bidding on placement of an advertisement within media content that is deliverable within a computer networking environment, the system comprising at least a processor and a memory, wherein the processor and/or memory are configured to perform the following operations:
 receiving specifications for a plurality of first advertisements that are each associated with a model configured to adjust a parameter value of a bid based on a plurality of different combinations of user characteristics and/or media content characteristics associated with different advertisement requests and/or advertisement characteristics associated with different advertisements;   receiving a first advertisement request for bidding for placement of an advertisement on a first advertisement space that is within a first publisher's media content that has been requested by a first user, and the first advertisement request is associated with a first set of user characteristics profile data and media content characteristics profile data;   for the first advertisement request and each of the first advertisements, inputting all or a subset of the first set of user characteristics profile data and/or media content characteristics profile data and/or advertisement characteristics data associated with such each first advertisement to each of the models so as to determine an associated parameter value;   determining a plurality of bids for placement of the plurality of first advertisements on the first advertisement space, wherein at least a first portion of the bids are determined based on the associated parameter values; and   selecting an optimum one of the determined bids and sending the optimum bid, along with a reference to the optimum bid's associated advertisement, from the bid determination platform to a sender of the first advertisement request.   
     
     
         23 . At least one non-transitory computer readable storage medium having computer program instructions stored thereon that are arranged to perform the following operations:
 at a bid determination platform, receiving specifications for a plurality of first advertisements that are each associated with a model configured to adjust a parameter value of a bid based on a plurality of different combinations of user characteristics and/or media content characteristics associated with different advertisement requests and/or advertisement characteristics associated with different advertisements;   at the bid determination platform, receiving a first advertisement request for bidding for placement of an advertisement on a first advertisement space that is within a first publisher's media content that has been requested by a first user, and the first advertisement request is associated with a first set of user characteristics profile data and media content characteristics profile data;   for the first advertisement request and each of the first advertisements, inputting all or a subset of the first set of user characteristics profile data and/or media content characteristics profile data and/or advertisement characteristics data associated with such each first advertisement to each of the models so as to determine an associated parameter value;   determining a plurality of bids for placement of the plurality of first advertisements on the first advertisement space, wherein at least a first portion of the bids are determined based on the associated parameter values; and   selecting an optimum one of the determined bids and sending the optimum bid, along with a reference to the optimum bid's associated advertisement, from the bid determination platform to a sender of the first advertisement request.