Predictive recommendation system using tiered feature data

Abstract

In general, embodiments of the present invention provide systems, methods and computer readable media for a predictive recommendation system using predictive models derived from tiered feature data.

1 - 33 . (canceled) 
     
     
         34 . A system, comprising one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to:
 determine a consumer identifier associated a consumer device that is selected to receive a first impressions set associated with one or more device rendered objects;   obtain, from a data repository, feature data associated with the consumer identifier;   calculate feature ratio data correlated to a feature type based at least in part on the feature data;   in an instance in which the feature ratio data satisfies a threshold feature ratio value, generate combined feature data based at least in part on the feature data and tiered feature data for a second impressions set associated with a tier group of device rendered objects;   select, based at least in part on the combined feature data, a subset of promotions from a plurality of promotions to be transmitted to the consumer device associated with the consumer identifier; and   transmit the subset of promotions to the consumer device associated with the consumer identifier for display via the consumer device.   
     
     
         35 . The system of  claim 34 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
 obtain the feature data from a portion of the data repository allocated for the feature type.   
     
     
         36 . The system of  claim 34 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
 train a machine learning model based at least in part on the feature data in the instance in which the feature ratio data satisfies the threshold feature ratio value.   
     
     
         37 . The system of  claim 34 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
 predict the feature type based at least in part on the feature data.   
     
     
         38 . The system of  claim 34 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
 update historical feature data stored in the data repository based at least in part on the feature data, wherein the historical feature data represents a portion of the tier group of device rendered objects that is related to the feature type.   
     
     
         39 . The system of  claim 38 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
 update one or more portions of the historical feature data based at least in part on predicted consumer behavior data associated with the feature data.   
     
     
         40 . The system of  claim 38 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
 update one or more portions of the historical feature data based at least in part on a predicted gender type associated with the consumer identifier.   
     
     
         41 . A computer-implemented method, comprising:
 determining, by a computing device comprising a processor, a consumer identifier associated a consumer device that is selected to receive a first impressions set associated with one or more device rendered objects;   obtaining, by the computing device and from a data repository, feature data associated with the consumer identifier;   calculating, by the computing device, feature ratio data correlated to a feature type based at least in part on the feature data;   in an instance in which the feature ratio data satisfies a threshold feature ratio value, generating, by the computing device, combined feature data based at least in part on the feature data and tiered feature data for a second impressions set associated with a tier group of device rendered objects;   selecting, by the computing device and based at least in part on the combined feature data, a subset of promotions from a plurality of promotions to be transmitted to the consumer device associated with the consumer identifier; and   transmitting, by the computing device, the subset of promotions to the consumer device associated with the consumer identifier for display via the consumer device.   
     
     
         42 . The computer-implemented method of  claim 41 , wherein the obtaining the feature data comprises obtaining the feature data from a portion of the data repository allocated for the feature type. 
     
     
         43 . The computer-implemented method of  claim 41 , further comprising:
 training, by the computing device, a machine learning model based at least in part on the feature data in the instance in which the feature ratio data satisfies the threshold feature ratio value.   
     
     
         44 . The computer-implemented method of  claim 41 , further comprising:
 predicting, by the computing device, the feature type based at least in part on the feature data.   
     
     
         45 . The computer-implemented method of  claim 41 , further comprising:
 updating, by the computing device, historical feature data stored in the data repository based at least in part on the feature data, wherein the historical feature data represents a portion of the tier group of device rendered objects that is related to the feature type.   
     
     
         46 . The computer-implemented method of  claim 45 , further comprising:
 updating, by the computing device, one or more portions of the historical feature data based at least in part on predicted consumer behavior data associated with the feature data.   
     
     
         47 . The computer-implemented method of  claim 45 , further comprising:
 updating, by the computing device, one or more portions of the historical feature data based at least in part on a predicted gender type associated with the consumer identifier.   
     
     
         48 . A computer program product, stored on a computer readable medium, comprising instructions that when executed by one or more computers cause the one or more computers to:
 determine a consumer identifier associated a consumer device that is selected to receive a first impressions set associated with one or more device rendered objects;   obtain, from a data repository, feature data associated with the consumer identifier;   calculate feature ratio data correlated to a feature type based at least in part on the feature data;   in an instance in which the feature ratio data satisfies a threshold feature ratio value, generate combined feature data based at least in part on the feature data and tiered feature data for a second impressions set associated with a tier group of device rendered objects;   select, based at least in part on the combined feature data, a subset of promotions from a plurality of promotions to be transmitted to the consumer device associated with the consumer identifier; and   transmit the subset of promotions to the consumer device associated with the consumer identifier for display via the consumer device.   
     
     
         49 . The computer program product of  claim 48 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:
 obtain the feature data from a portion of the data repository allocated for the feature type.   
     
     
         50 . The computer program product of  claim 48 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:
 train a machine learning model based at least in part on the feature data in the instance in which the feature ratio data satisfies the threshold feature ratio value.   
     
     
         51 . The computer program product of  claim 48 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:
 update historical feature data stored in the data repository based at least in part on the feature data, wherein the historical feature data represents a portion of the tier group of device rendered objects that is related to the feature type.   
     
     
         52 . The computer program product of  claim 51 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:
 update one or more portions of the historical feature data based at least in part on predicted consumer behavior data associated with the feature data.   
     
     
         53 . The computer program product of  claim 51 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:
 update one or more portions of the historical feature data based at least in part on a predicted gender type associated with the consumer identifier.