METHOD AND SYSTEM FOR GENERATING PURCHASE RECOMMENDATIONS BASED ON PURCHASE CATEGORY ASSOCIATIONS
Embodiments provide a computer-executable method, computer system and non-transitory computer-readable medium for programmatically generating an association among two or more purchase categories based on purchase data of a plurality of consumers. The method includes programmatically accessing, from a dataset via a network device, prior purchase data associated with purchases of a plurality of commercial objects by a plurality of consumers. The method also includes programmatically identifying a plurality of categories associated with the plurality of commercial objects. The method also includes, for each consumer in the plurality of consumers, programmatically generating a total number of purchases by the consumer in each category in the plurality of categories. The method further includes generating, using a processor of a computing device, a category association score between each pair of categories in the plurality of categories by programmatically analyzing similarities among the total numbers of purchases in the plurality of categories for the plurality of consumers.
1 .- 25 . (canceled)
26 . One or more non-transitory computer-readable media having encoded thereon one or more computer-executable instructions that, when executed on a computer, cause the computer to:
programmatically access consumer profile data associated with a consumer profile, wherein the consumer profile data comprises one or more profile data items associated with one or more respective interests associated with the consumer profile;
determine, based on the one or more profile data items comprised in the consumer profile data, a set of categories of interest;
programmatically access a category association dataset, wherein the category association dataset comprises one or more pairs of categories, and wherein each of the one or more pairs of categories is associated with a category association score;
determine, for each category of interest in the set of categories of interest, one or more respective associated categories, wherein each category of interest and the one or more respective associated categories make up one or more associated category pairs, and wherein the one or more associated category pairs represent a subset of the category association dataset;
rank, based on the category association score, each of the one or more associated category pairs;
compare the category association score associated with the one or more ranked associated category pairs to a predefined category association threshold and, in circumstances in which the category association score satisfies the predefined category association threshold, add the one or more ranked associated category pairs to a recommended category set;
determine one or more recommended categories from the one or more ranked associated category pairs comprised in the recommended category set;
determine one or more recommended commercial objects associated with the one or more recommended categories to select for the consumer profile; and
transmit, to a consumer computing device associated with the consumer profile, one or more computer-executable instructions to cause the consumer computing device to visually display one or more impressions associated with the one or more recommended commercial objects selected for the user profile.
27 . The one or more non-transitory computer-readable media of claim 26 , wherein the one or more computer-executable instructions configured to determine one or more recommended commercial objects associated with the one or more recommended categories further cause the computer to:
rank the one or more recommended commercial objects based on the category association scores associated with the one or more recommended categories related to the one or more recommended commercial objects; and
determine, based on a recommended commercial object threshold, which of the one or more recommended commercial objects to select for the consumer profile.
28 . The one or more non-transitory computer-readable media of claim 26 , wherein the one or more computer-executable instructions configured to determine the set of categories of interest further cause the computer to:
determine, based on the consumer profile data associated with the consumer profile, a first category of interest; and
determine, based on prior purchase data associated with the consumer profile, a second category of interest.
29 . The one or more non-transitory computer-readable media of claim 28 , wherein the one or more computer-executable instructions configured to determine the set of categories of interest further cause the computer to:
determine a third category of interest related to both the first category of interest and the second category of interest;
determine whether a category association score associated with the first category of interest, the second category of interest, and the third category of interest satisfies a predefined category association threshold; and
determine a recommended commercial object associated with the third category of interest to select for the user profile.
30 . The one or more non-transitory computer-readable media of claim 26 , wherein the one or more ranked associated category pairs must satisfy a ranking position threshold in order to be added to the recommended category set.
31 . The one or more non-transitory computer-readable media of claim 26 , wherein the one or more computer-executable instructions further cause the computer to:
determine, based on prior purchase data associated with the user profile, a purchase probability score, wherein the purchase probability score indicates a probability that a commercial object associated with a particular category of interest will be purchased.
32 . The one or more non-transitory computer-readable media of claim 31 , wherein the prior purchase data comprises as least one of purchased commercial object data, category data associated with the purchased commercial object data, purchase price data, purchase time period data, merchant data, or consumer identification data.
33 . A computer-implemented method, the method comprising:
programmatically accessing consumer profile data associated with a consumer profile, wherein the consumer profile data comprises one or more profile data items associated with one or more respective interests associated with the consumer profile;
determining, based on the one or more profile data items comprised in the consumer profile data, a set of categories of interest;
programmatically accessing a category association dataset, wherein the category association dataset comprises one or more pairs of categories, and wherein each of the one or more pairs of categories is associated with a category association score;
determining, for each category of interest in the set of categories of interest, one or more respective associated categories, wherein each category of interest and the one or more respective associated categories make up one or more associated category pairs, and wherein the one or more associated category pairs represent a subset of the category association dataset;
ranking, based on the category association score, each of the one or more associated category pairs;
comparing the category association score associated with the one or more ranked associated category pairs to a predefined category association threshold and, in circumstances in which the category association score satisfies the predefined category association threshold, add the one or more ranked associated category pairs to a recommended category set;
determining one or more recommended categories from the one or more ranked associated category pairs comprised in the recommended category set;
determining one or more recommended commercial objects associated with the one or more recommended categories to select for the consumer profile; and
transmitting, to a consumer computing device associated with the consumer profile, one or more computer-executable instructions to cause the consumer computing device to visually display one or more impressions associated with the one or more recommended commercial objects selected for the user profile.
34 . The computer-implemented method of claim 33 , wherein determining one or more recommended commercial objects associated with the one or more recommended categories further comprises:
ranking the one or more recommended commercial objects based on the category association scores associated with the one or more recommended categories related to the one or more recommended commercial objects; and
determining, based on a recommended commercial object threshold, which of the one or more recommended commercial objects to select for the consumer profile.
35 . The computer-implemented method of claim 33 , wherein determining the set of categories of interest further comprises:
determining, based on the consumer profile data associated with the consumer profile, a first category of interest; and
determining, based on prior purchase data associated with the consumer profile, a second category of interest.
36 . The computer-implemented method of claim 35 , wherein determining the set of categories of interest further comprises:
determining a third category of interest related to both the first category of interest and the second category of interest;
determining whether a category association score associated with the first category of interest, the second category of interest, and the third category of interest satisfies a predefined category association threshold; and
determining a recommended commercial object associated with the third category of interest to select for the user profile.
37 . The computer-implemented method of claim 33 , wherein the one or more ranked associated category pairs must satisfy a ranking position threshold in order to be added to the recommended category set.
38 . The computer-implemented method of claim 33 , the method further comprising:
determining, based on prior purchase data associated with the user profile, a purchase probability score, wherein the purchase probability score indicates a probability that a commercial object associated with a particular category of interest will be purchased.
39 . The computer-implemented method of claim 38 , wherein the prior purchase data comprises as least one of purchased commercial object data, category data associated with the purchased commercial object data, purchase price data, purchase time period data, merchant data, or consumer identification data.
40 . 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:
programmatically accessing consumer profile data associated with a consumer profile, wherein the consumer profile data comprises one or more profile data items associated with one or more respective interests associated with the consumer profile;
determining, based on the one or more profile data items comprised in the consumer profile data, a set of categories of interest;
programmatically accessing a category association dataset, wherein the category association dataset comprises one or more pairs of categories, and wherein each of the one or more pairs of categories is associated with a category association score;
determining, for each category of interest in the set of categories of interest, one or more respective associated categories, wherein each category of interest and the one or more respective associated categories make up one or more associated category pairs, and wherein the one or more associated category pairs represent a subset of the category association dataset;
ranking, based on the category association score, each of the one or more associated category pairs;
comparing the category association score associated with the one or more ranked associated category pairs to a predefined category association threshold and, in circumstances in which the category association score satisfies the predefined category association threshold, add the one or more ranked associated category pairs to a recommended category set;
determining one or more recommended categories from the one or more ranked associated category pairs comprised in the recommended category set;
determining one or more recommended commercial objects associated with the one or more recommended categories to select for the consumer profile; and
transmitting, to a consumer computing device associated with the consumer profile, one or more computer-executable instructions to cause the consumer computing device to visually display one or more impressions associated with the one or more recommended commercial objects selected for the user profile.
41 . The computer program product of claim 40 , wherein determining one or more recommended commercial objects associated with the one or more recommended categories further comprises:
ranking the one or more recommended commercial objects based on the category association scores associated with the one or more recommended categories related to the one or more recommended commercial objects; and
determining, based on a recommended commercial object threshold, which of the one or more recommended commercial objects to select for the consumer profile.
42 . The computer program product of claim 40 , wherein determining the set of categories of interest further comprises:
determining, based on the consumer profile data associated with the consumer profile, a first category of interest; and
determining, based on prior purchase data associated with the consumer profile, a second category of interest.
43 . The computer program product of claim 42 , wherein determining the set of categories of interest further comprises:
determining a third category of interest related to both the first category of interest and the second category of interest;
determining whether a category association score associated with the first category of interest, the second category of interest, and the third category of interest satisfies a predefined category association threshold; and
determining a recommended commercial object associated with the third category of interest to select for the user profile.
44 . The computer program product of claim 40 , wherein the one or more ranked associated category pairs must satisfy a ranking position threshold in order to be added to the recommended category set.
45 . The computer program product of claim 40 , the computer program product further configured for:
determining, based on prior purchase data associated with the user profile, a purchase probability score, wherein the purchase probability score indicates a probability that a commercial object associated with a particular category of interest will be purchased.