Method, apparatus, and computer program product for determining a provider return rate
View Patent ↗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. A method for classifying providers based on a return rate of a provider, comprising the steps of:
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 return rate of a provider is likely to satisfy a predetermined threshold,
wherein the return rate is indicative of a rate at which refunds of a purchase price are requested, and
wherein the determination of whether the return rate of the provider is likely to satisfy the predetermined threshold is made by:
determining, based on the plurality of available attributes, a classifying model from the set of classifying models to utilize,
wherein each classifying model of the set of classifying models is trained to utilize a set of determinative attributes, and
wherein the determination of the 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;
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 return rate; 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 return rate of the provider is likely to satisfy the redetermined threshold and a second class of the two classes is indicative of a determination that the return rate of the provider is not likely to satisfy the predetermined threshold.
2. The method according to claim 1 , wherein the classifying model is a support vector machine.
3. The method according to claim 1 , further comprising determining which one of a plurality of classifying models to utilize based on available attribute data.
4. The method according to claim 1 , wherein the corresponding attributes are assembled from one or more of (1) internal data, (2) external data, and (3) web data.
5. The method according to claim 1 , further comprising generating the plurality of attributes by normalizing a plurality of raw data.
6. The method according to claim 1 , wherein the corresponding attributes comprises one or more of category data, sub-category data, and competitor feature data.
7. The method according to claim 1 , wherein corresponding attributes comprises one or more of time data, financial stability risk data, median credit data, count of judgment data, and risk level data.
8. The method according to claim 1 , wherein the corresponding attributes comprise web data.
9. 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 attributes corresponding to the provider;
determine whether a return rate of a provider is likely to satisfy a predetermined threshold,
wherein the return rate is indicative of a rate at which refunds of a purchase price are requested, and
wherein the computer code configured to cause the apparatus to determine whether the return rate of the provider is likely to satisfy the predetermined threshold further comprises computer code configured to cause the apparatus to:
determine, based on the plurality of available attributes, a classifying model from the set of classifying models to utilize,
wherein each classifying model of the set of classifying models is trained to utilize a set of determinative attributes, and
wherein the determination of the 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;
identify 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 return rate; and
identify 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 return rate 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 return rate of the provider is not likely to satisfy the predetermined threshold.
10. The apparatus of claim 9 , wherein the classifying model is a support vector machine.
11. The apparatus of claim 9 , wherein the at least one memory and computer program code are configured to, with the at least one processor, cause the apparatus to determine which one of a plurality of classifying models to utilize based on available attribute data.
12. The apparatus of claim 9 , wherein the corresponding attributes are assembled from one or more of (1) internal data, (2) external data, and (3) web data.
13. The apparatus of claim 9 , wherein the at least one memory and computer program code are configured to, with the at least one processor, cause the apparatus to generate the plurality of attributes by normalizing a plurality of raw data.
14. The apparatus of claim 9 , wherein the corresponding attributes comprises one or more of category data, sub-category data, and competitor feature data.
15. The apparatus of claim 9 , wherein corresponding attributes comprises one or more of time data, financial stability risk data, median credit data, count of judgment data, and risk level data.
16. The apparatus of claim 9 , wherein the corresponding attributes comprise web data.
17. 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 attributes corresponding to the provider;
determining whether a return rate of a provider is likely to satisfy a predetermined threshold,
wherein the return rate is indicative of a rate at which refunds of a purchase price are requested, and
wherein the determination of whether the return rate of the provider is likely to satisfy the predetermined threshold is made by:
determining, based on the plurality of available attributes, a classifying model from the set of classifying models to utilize,
wherein each classifying model of the set of classifying models is trained to utilize a set of determinative attributes, and
wherein the determination of the 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;
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 return rate; 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 return rate 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 return rate of the provider is not likely to satisfy the predetermined threshold.
18. A computer program product according to claim 17 , wherein the classifying model is a support vector machine.
19. A computer program product according to claim 17 , wherein the computer-executable program code portions further comprise program code instructions for determining which one of a plurality of classifying models to utilize based on available attribute data.
20. A computer program product according to claim 17 , wherein the corresponding attributes are assembled from one or more of (1) internal data, (2) external data, and (3) web data.
21. A computer program product according to claim 17 , wherein the computer-executable program code portions further comprise program code instructions for generating the plurality of attributes by normalizing a plurality of raw data.
22. A computer program product according to claim 17 , wherein the corresponding attributes comprises one or more of category data, sub-category data, and competitor feature data.
23. A computer program product according to claim 17 , wherein corresponding attributes comprises one or more of time data, financial stability risk data, median credit data, count of judgment data, and risk level data.
24. A computer program product according to claim 17 , wherein the corresponding attributes comprise web data.