Method, apparatus, and computer program product for merchant classification

Abstract

Embodiments of the present invention provide methods, systems, apparatuses, and computer program products for classifying merchants. In one embodiment a method is provided comprising determining, based on a first value, a first prediction value that indicates a programmatically expected number of consumers that will request termination of an accepted first promotion; and determining, based on the first prediction value, a classification for the first entity, the classification specifying a likelihood that the transmittal of the first promotion to consumers will result in a number of terminations less than a pre-specified threshold.

1 - 48 . (canceled) 
     
     
         49 . 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 attributes for promotions offered via a promotion and marketing service system;   select a subset of the attributes from an attribute pool related to defined classification criteria for classifying entities;   train, based on the subset of the attributes selected from the attribute pool, a machine learning decision tree model by continuously selecting statistically significant attributes based on past performance data until quality criteria for the machine learning decision tree model is satisfied, wherein the machine learning decision tree model employs a value associated with a maximum number of promotions that an entity is capable of satisfying;   determine, using the machine learning decision tree model, a prediction value, wherein the prediction value indicates a programmatically predicted number of consumers that will request termination of an accepted promotion within a period of time from transmittal of the accepted promotion to respective electronic interfaces of one or more consumer devices;   generate, based at least in part on the prediction value, an electronic communication for the one or more consumer devices, wherein the electronic communication comprises a promotion that satisfies a defined criterion associated with the prediction value; and   transmit the electronic communication to the one or more consumer devices.   
     
     
         50 . The system of  claim 49 , 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:
 determine, based on the prediction value, a classification for the entity, the classification specifying a likelihood that the transmittal of the accepted promotion to the one or more consumer devices will result in a number of terminations less than a pre-specified threshold.   
     
     
         51 . The system of  claim 50 , 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:
 in response to determining that the classification satisfies a defined criterion, transmit the electronic communication to the one or more consumer devices.   
     
     
         52 . The system of  claim 49 , 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:
 determine the prediction value based on one or more decision trees associated with the machine learning decision tree model.   
     
     
         53 . The system of  claim 49 , 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:
 determine the prediction value based on two or more decision trees of a random forest classifier associated with the machine learning decision tree model.   
     
     
         54 . The system of  claim 49 , 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:
 select the subset of the attributes for a decision tree associated with the machine learning decision tree model.   
     
     
         55 . The system of  claim 49 , wherein the subset of the attributes is a first subset of the attributes, wherein the defined classification criteria is first defined classification criteria, and 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:
 select a second subset of the attributes from the attribute pool related to second defined classification criteria for classifying the entities.   
     
     
         56 . The system of  claim 55 , 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:
 generate a first decision tree associated with the machine learning decision tree model based on the first subset of the attributes; and   generate a second decision tree associated with the machine learning decision tree model based on the second subset of the attributes.   
     
     
         57 . The system of  claim 56 , wherein the prediction value is a first prediction value, and 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:
 determine the first prediction value using the first decision tree; and   determine a second prediction value using the second decision tree.   
     
     
         58 . The system of  claim 57 , 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:
 generate the electronic communication for the one or more consumer devices based at least in part on the first prediction value and the second prediction value.   
     
     
         59 . A computer-implemented method, comprising:
 determining, by a computing device comprising a processor, attributes for promotions offered via a promotion and marketing service system;   selecting, by the computing device, a subset of the attributes from an attribute pool related to defined classification criteria for classifying entities;   training, by the computing device and based on the subset of the attributes selected from the attribute pool, a machine learning decision tree model by continuously selecting statistically significant attributes based on past performance data until quality criteria for the machine learning decision tree model is satisfied, wherein the machine learning decision tree model employs a value associated with a maximum number of promotions that an entity is capable of satisfying;   determining, by the computing device and using the machine learning decision tree model, a prediction value, wherein the prediction value indicates a programmatically predicted number of consumers that will request termination of an accepted promotion within a period of time from transmittal of the accepted promotion to respective electronic interfaces of one or more consumer devices;   generating, by the computing device and based at least in part on the prediction value, an electronic communication for the one or more consumer devices, wherein the electronic communication comprises a promotion that satisfies a defined criterion associated with the prediction value; and   transmitting, by the computing device, the electronic communication to the one or more consumer devices.   
     
     
         60 . The computer-implemented method of  claim 59 , further comprising:
 determining, by the computing device and based on the prediction value, a classification for the entity, the classification specifying a likelihood that the transmittal of the accepted promotion to the one or more consumer devices will result in a number of terminations less than a pre-specified threshold.   
     
     
         61 . The computer-implemented method of  claim 60 , wherein the transmitting comprises transmitting the electronic communication to the one or more consumer devices in response to determining that the classification satisfies a defined criterion. 
     
     
         62 . The computer-implemented method of  claim 59 , wherein the subset of the attributes is a first subset of the attributes, the defined classification criteria is first defined classification criteria, and the computer-implemented method further comprising:
 selecting, by the computing device, a second subset of the attributes from the attribute pool related to second defined classification criteria for classifying the entities.   
     
     
         63 . The computer-implemented method of  claim 62 , further comprising:
 generating, by the computing device, a first decision tree associated with the machine learning decision tree model based on the first subset of the attributes; and   generating, by the computing device, a second decision tree associated with the machine learning decision tree model based on the second subset of the attributes.   
     
     
         64 . The computer-implemented method of  claim 63 , wherein the prediction value is a first prediction value, and the computer-implemented method further comprising:
 determining, by the computing device, the first prediction value using the first decision tree; and   determining, by the computing device, a second prediction value using the second decision tree.   
     
     
         65 . The computer-implemented method of  claim 64 , further comprising:
 generating, by the computing device, the electronic communication for the one or more consumer devices based at least in part on the first prediction value and the second prediction value.   
     
     
         66 . A computer program product, stored on a non-transitory computer readable medium, comprising instructions that when executed by one or more computers cause the one or more computers to:
 determine attributes for promotions offered via a promotion and marketing service system;   select a subset of the attributes from an attribute pool related to defined classification criteria for classifying entities;   train, based on the subset of the attributes selected from the attribute pool, a machine learning decision tree model by continuously selecting statistically significant attributes based on past performance data until quality criteria for the machine learning decision tree model is satisfied, wherein the machine learning decision tree model employs a value associated with a maximum number of promotions that an entity is capable of satisfying;   determine, using the machine learning decision tree model, a prediction value, wherein the prediction value indicates a programmatically predicted number of consumers that will request termination of an accepted promotion within a period of time from transmittal of the accepted promotion to respective electronic interfaces of one or more consumer devices;   generate, based at least in part on the prediction value, an electronic communication for the one or more consumer devices, wherein the electronic communication comprises a promotion that satisfies a defined criterion associated with the prediction value; and   transmit the electronic communication to the one or more consumer devices.   
     
     
         67 . The computer program product of  claim 66 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:
 determine, based on the prediction value, a classification for the entity, the classification specifying a likelihood that the transmittal of the accepted promotion to the one or more consumer devices will result in a number of terminations less than a pre-specified threshold.   
     
     
         68 . The computer program product of  claim 67 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:
 in response to determining that the classification satisfies a defined criterion, transmit the electronic communication to the one or more consumer devices.