Method, apparatus, and computer program product for determining a provider return rate

Abstract

Provided herein are systems, methods and computer readable media for classifying a provider of products, services or experiences as a provider that should be engaged based on a predicted return rate for any products, services or experiences that may be offered and purchased by a consumer. An example method may comprise supplying a classifying model with a dataset, wherein the dataset comprises an identification of a provider and a plurality of attributes corresponding to the provider and identifying a class of the provider in accordance with the plurality of corresponding attributes, wherein the identification is determined based on one or more patterns determinative of a return rate by the classifying model.

1 .- 48 . (canceled) 
     
     
         49 . A method comprising:
 supplying a set of classifying models with a dataset, wherein the dataset comprises an identification of a provider and a plurality of available attributes corresponding to the provider; and   determining whether a value of a particular attribute of a particular provider is likely to satisfy a predetermined threshold, and   wherein the determination of whether the value of the particular attribute of the provider is likely to satisfy the predetermined threshold comprises:
 determining an availability of a value of a second attribute within the plurality of available attributes; 
 in an instance in which the availability of the value of the second attribute is determined, utilizing a first classifying model; 
 in an instance in which an unavailability of the value of the second attribute is determined, utilizing a second classifying model; 
 wherein each classifying model of the set of classifying models is trained to utilize a set of determinative attributes, and 
 identifying one or more patterns of available attributes that match one or more patterns found in the set of determinative attributes, 
 wherein each of one or more patterns is indicative of a known value of the second attribute; and 
 identifying which of two classes to assign the provider in accordance with the identified patterns, 
 wherein a first class of the two classes is indicative of a determination that the value of the particular attribute of the provider is likely to satisfy the predetermined threshold and a second class of the two classes is indicative of a determination that the value of the particular attribute of the provider is not likely to satisfy the predetermined threshold; and 
   assigning a label to the provider, the label indicative of the class to which the provider is identified, the label assigned by the machine learning classification of the provider based on the value of the particular attribute of the provider.   
     
     
         50 . The method according to  claim 49 , further comprising determining, subsequent to determining the availability of the value of the second attribute, which one of a first subset of classifying models to utilize based on available attribute data, the first subset of classifying models comprising at the first classifying model. 
     
     
         51 . The method according to  claim 49 , further comprising determining, subsequent to determining the unavailability of the value of the second attribute, which one of a second subset of classifying models to utilize based on available attribute data, the second subset of classifying models comprising at the second classifying model. 
     
     
         52 . The method according to  claim 51 , wherein the determination of the first classifying model comprises matching the plurality of available attributes to the classifying model requiring at least a subset of the available attributes as determinative attributes. 
     
     
         53 . The method according to  claim 52 , wherein the determination of the second classifying model comprises matching the plurality of available attributes to the classifying model requiring at least a subset of the available attributes as determinative attributes. 
     
     
         54 . The method according to  claim 49 , wherein the corresponding attributes are assembled from one or more of (1) internal data, (2) external data, and (3) web data,
 wherein the corresponding attributes assembled from the internal data comprise one or more of category data, sub-category data, and competitor feature data.   
     
     
         55 . The method according to  claim 49 , further comprising generating the plurality of attributes by normalizing a plurality of raw data. 
     
     
         56 . The method according to  claim 49 , wherein the classifying model is a support vector machine. 
     
     
         57 . An apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to:
 supply a set of classifying models with a dataset, wherein the dataset comprises an identification of a provider and a plurality of available attributes corresponding to the provider; and   determine whether a value of a particular attribute of a particular provider is likely to satisfy a predetermined threshold, and   wherein the determination of whether the value of the particular attribute of the provider is likely to satisfy the predetermined threshold comprises:
 determining an availability of a value of a second attribute within the plurality of available attributes; 
 in an instance in which the availability of the value of the second attribute is determined, utilizing a first classifying model; 
 in an instance in which an unavailability of the value of the second attribute is determined, utilizing a second classifying model; 
 wherein each classifying model of the set of classifying models is trained to utilize a set of determinative attributes, and 
 identifying one or more patterns of available attributes that match one or more patterns found in the set of determinative attributes, 
 wherein each of one or more patterns is indicative of a known value of the second attribute; and 
 identifying which of two classes to assign the provider in accordance with the identified patterns, 
 wherein a first class of the two classes is indicative of a determination that the value of the particular attribute of the provider is likely to satisfy the predetermined threshold and a second class of the two classes is indicative of a determination that the value of the particular attribute of the provider is not likely to satisfy the predetermined threshold; and 
   assign a label to the provider, the label indicative of the class to which the provider is identified, the label assigned by the machine learning classification of the provider based on the value of the particular attribute of the provider.   
     
     
         58 . The apparatus according to  claim 57 , wherein the at least one memory and computer program code are configured to, with the at least one processor, cause the apparatus to determine, subsequent to determining the availability of the value of the second attribute, which one of a first subset of classifying models to utilize based on available attribute data, the first subset of classifying models comprising at the first classifying model. 
     
     
         59 . The apparatus according to  claim 57 , wherein the at least one memory and computer program code are configured to, with the at least one processor, cause the apparatus to determine, subsequent to determining the unavailability of the value of the second attribute, which one of a second subset of classifying models to utilize based on available attribute data, the second subset of classifying models comprising at the second classifying model. 
     
     
         60 . The apparatus according to  claim 58 , wherein the determination of the first classifying model comprises matching the plurality of available attributes to the classifying model requiring at least a subset of the available attributes as determinative attributes. 
     
     
         61 . The apparatus according to  claim 59 , wherein the determination of the second classifying model comprises matching the plurality of available attributes to the classifying model requiring at least a subset of the available attributes as determinative attributes. 
     
     
         62 . The apparatus according to  claim 57 , wherein the corresponding attributes are assembled from one or more of (1) internal data, (2) external data, and (3) web data,
 wherein the corresponding attributes assembled from the internal data comprise one or more of category data, sub-category data, and competitor feature data.   
     
     
         63 . The apparatus according to  claim 57 , further comprising generating the plurality of attributes by normalizing a plurality of raw data. 
     
     
         64 . The apparatus according to  claim 57 , wherein the classifying model is a support vector machine. 
     
     
         65 . A computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code instructions stored therein, the computer-executable program code instructions comprising program code instructions for:
 supplying a set of classifying models with a dataset, wherein the dataset comprises an identification of a provider and a plurality of available attributes corresponding to the provider; and   determining whether a value of a particular attribute of a particular provider is likely to satisfy a predetermined threshold, and   wherein the determination of whether the value of the particular attribute of the provider is likely to satisfy the predetermined threshold comprises:
 determining an availability of a value of a second attribute within the plurality of available attributes; 
 in an instance in which the availability of the value of the second attribute is determined, utilizing a first classifying model; 
 in an instance in which an unavailability of the value of the second attribute is determined, utilizing a second classifying model; 
 wherein each classifying model of the set of classifying models is trained to utilize a set of determinative attributes, and 
 identifying one or more patterns of available attributes that match one or more patterns found in the set of determinative attributes, 
 wherein each of one or more patterns is indicative of a known value of the second attribute; and 
 identifying which of two classes to assign the provider in accordance with the identified patterns, 
 wherein a first class of the two classes is indicative of a determination that the value of the particular attribute of the provider is likely to satisfy the predetermined threshold and a second class of the two classes is indicative of a determination that the value of the particular attribute of the provider is not likely to satisfy the predetermined threshold; and 
   assigning a label to the provider, the label indicative of the class to which the provider is identified, the label assigned by the machine learning classification of the provider based on the value of the particular attribute of the provider.   
     
     
         66 . The computer program product according to  claim 65 , wherein the computer-executable program code portions further comprise program code instructions for determining, subsequent to determining the availability of the value of the second attribute, which one of a first subset of classifying models to utilize based on available attribute data, the first subset of classifying models comprising at the first classifying model. 
     
     
         67 . The method according to  claim 49 , wherein the computer-executable program code portions further comprise program code instructions for determining, subsequent to determining the unavailability of the value of the second attribute, which one of a second subset of classifying models to utilize based on available attribute data, the second subset of classifying models comprising at the second classifying model. 
     
     
         68 . The computer program product according to  claim 66 , wherein the determination of the first classifying model comprises matching the plurality of available attributes to the classifying model requiring at least a subset of the available attributes as determinative attributes. 
     
     
         69 . The computer program product according to  claim 67 , wherein the determination of the second classifying model comprises matching the plurality of available attributes to the classifying model requiring at least a subset of the available attributes as determinative attributes. 
     
     
         70 . The computer program product according to  claim 65 , wherein the corresponding attributes are assembled from one or more of (1) internal data, (2) external data, and (3) web data,
 wherein the corresponding attributes assembled from the internal data comprise one or more of category data, sub-category data, and competitor feature data.   
     
     
         71 . The computer program product according to  claim 65 , further comprising generating the plurality of attributes by normalizing a plurality of raw data. 
     
     
         72 . The computer program product according to  claim 65 , wherein the classifying model is a support vector machine.