Apparatus and method for enhanced message targeting

Abstract

A method, apparatus, and computer program product are disclosed for improved promotion targeting. An example apparatus includes a processor configured to cause retrieval of historical information regarding transactions associated with a plurality of identifier entities. The example apparatus further includes modeling circuitry configured to train a statistical model using the retrieved historical information, and estimate, using the statistical model, values for expected identifier entity transaction requests associated with each of the plurality of identifier entities. The processor of the example apparatus may further be configured to select, based on the estimated values, a subset of identifier entities to receive impressions of the promotion, and the apparatus may further include communications circuitry configured to transmit an impression of the promotion to each identifier entity in the subset.

1 - 24 . (canceled) 
     
     
         25 . An apparatus for improved machine learning, the apparatus comprising at least one processor and at least one non-transitory memory having computer-coded instructions stored thereon that, in execution with the at least one processor, causes the apparatus to:
 receive training data representing transactions associated with a plurality of identifier entities, the training data comprising at least one measured characteristic associated with at least one promotion,   wherein the plurality of identifier entities are indicated similar to a target identifier entity;   train a model that predicts an expected incremental booking value associated with the target identifier entity for a prospective promotion, wherein to train the model the apparatus is caused to:
 estimate an expected impact of the at least one measured characteristic on a calculated incremental booking value based at least in part on a first subset of the training data associated with a control group of identifier entities that are indicated as not provided with a selected promotion of the at least one promotion, and a second subset of the training data associated with a target group of identifier entities that are indicated as provided with the selected promotion; and 
 train the model based at least in part on the expected impact of the at least one measured characteristic. 
   
     
     
         26 . The apparatus of  claim 25 , wherein the at least one measured characteristic comprises, for each identifier entity of the plurality of identifier entities, a number of purchases associated with the identifier entity with a promotion and marketing system. 
     
     
         27 . The apparatus of  claim 25 , wherein the prospective promotion is indicated similar to the selected promotion. 
     
     
         28 . The apparatus of  claim 25 , the apparatus further caused to transmit an impression of the prospective promotion to a computing device associated with the target identifier entity. 
     
     
         29 . The apparatus of  claim 25 , wherein apparatus is further caused to determine that the plurality of identifier entities are similar to the target identifier entity based at least in part on (i) consumer characteristic data associated with the plurality of identifier entities and the target identifier entity or (ii) historical behavior data associated with the plurality of identifier entities and the target identifier entity. 
     
     
         30 . The apparatus of  claim 25 , the apparatus further caused to:
 predict, using the model, a plurality of expected incremental booking values associated with a plurality of target identifier entities.   
     
     
         31 . The apparatus of  claim 30 , the apparatus further caused to:
 select a subset of the plurality of target identifier entities based at least in part on the plurality of expected incremental booking values; and   transmit an impression of the prospective promotion to a plurality of computing devices, the plurality of computing devices comprising at least one computing device associated with each target identifier entity of the subset of the plurality of target identifier entities.   
     
     
         32 . A computer-implemented method comprising:
 receiving training data representing transactions associated with a plurality of identifier entities, the training data comprising at least one measured characteristic associated with at least one promotion,   wherein the plurality of identifier entities are indicated similar to a target identifier entity;   training a model that predicts an expected incremental booking value associated with the target identifier entity for a prospective promotion by at least:
 estimating an expected impact of the at least one measured characteristic on a calculated incremental booking value based at least in part on a first subset of the training data associated with a control group of identifier entities that are indicated as not provided with a selected promotion of the at least one promotion, and a second subset of the training data associated with a target group of identifier entities that are indicated as provided with the selected promotion; and 
 training the model based at least in part on the expected impact of the at least one measured characteristic. 
   
     
     
         33 . The computer-implemented method of  claim 32 , wherein the at least one measured characteristic comprises, for each identifier entity of the plurality of identifier entities, a number of purchases associated with the identifier entity with a promotion and marketing system. 
     
     
         34 . The computer-implemented method of  claim 32 , wherein the prospective promotion is indicated similar to the selected promotion. 
     
     
         35 . The computer-implemented method of  claim 32 , the computer-implemented method further comprising transmitting an impression of the prospective promotion to a computing device associated with the target identifier entity. 
     
     
         36 . The computer-implemented method of  claim 32 , the computer-implemented method further comprising determining that the plurality of identifier entities are similar to the target identifier entity based at least in part on (i) consumer characteristic data associated with the plurality of identifier entities and the target identifier entity or (ii) historical behavior data associated with the plurality of identifier entities and the target identifier entity. 
     
     
         37 . The computer-implemented method of  claim 32 , the computer-implemented method further comprising:
 predicting, using the model, a plurality of expected incremental booking values associated with a plurality of target identifier entities.   
     
     
         38 . The computer-implemented method of  claim 37 , the computer-implemented method further comprising:
 selecting a subset of the plurality of target identifier entities based at least in part on the plurality of expected incremental booking values; and   transmitting an impression of the prospective promotion to a plurality of computing devices, the plurality of computing devices comprising at least one computing device associated with each target identifier entity of the subset of the plurality of target identifier entities.   
     
     
         39 . A computer program product comprising at least one non-transitory computer-readable storage medium having computer program code stored thereon that, in execution with at least one processor, is configured for:
 receiving training data representing transactions associated with a plurality of identifier entities, the training data comprising at least one measured characteristic associated with at least one promotion,   wherein the plurality of identifier entities are indicated similar to a target identifier entity;   training a model that predicts an expected incremental booking value associated with the target identifier entity for a prospective promotion by at least:
 estimating an expected impact of the at least one measured characteristic on a calculated incremental booking value based at least in part on a first subset of the training data associated with a control group of identifier entities that are indicated as not provided with a selected promotion of the at least one promotion, and a second subset of the training data associated with a target group of identifier entities that are indicated as provided with the selected promotion; and 
 training the model based at least in part on the expected impact of the at least one measured characteristic. 
   
     
     
         40 . The computer program product of  claim 39 , wherein the at least one measured characteristic comprises, for each identifier entity of the plurality of identifier entities, a number of purchases associated with the identifier entity with a promotion and marketing system. 
     
     
         41 . The computer program product of  claim 39 , wherein the prospective promotion is indicated similar to the selected promotion. 
     
     
         42 . The computer program product of  claim 39 , the computer program product further configured for determining that the plurality of identifier entities are similar to the target identifier entity based at least in part on (i) consumer characteristic data associated with the plurality of identifier entities and the target identifier entity or (ii) historical behavior data associated with the plurality of identifier entities and the target identifier entity. 
     
     
         43 . The computer program product of  claim 39 , the computer program product further configured for:
 predicting, using the model, a plurality of expected incremental booking values associated with a plurality of target identifier entities.   
     
     
         44 . The computer program product of  claim 43 , the computer program product further configured for:
 selecting a subset of the plurality of target identifier entities based at least in part on the plurality of expected incremental booking values; and   transmitting an impression of the prospective promotion to a plurality of computing devices, the plurality of computing devices comprising at least one computing device associated with each target identifier entity of the subset of the plurality of target identifier entities.