Learning systems for pangenetic-based recommendations
An embodiment may involve storing, by a computing device and in a database, a set of pangenetic attributes of a set of individuals, wherein the pangenetic attributes of the set are respectively and statistically associated with products; based on the statistical associations between the pangenetic attributes and the products, determining, by the computing device, product recommendations for a second set of individuals; receiving, by the computing device and from the second set of individuals, a plurality of measures of satisfaction with the product recommendations; based on the plurality of measures of satisfaction, learning, by the computing device, an association between a subset of the pangenetic attributes and a particular product; and storing, by the computing device and in the database, the learned association, wherein the learned association provides a basis for subsequent recommendations of the particular product when a subsequent individual exhibits the subset of the pangenetic attributes.
1. A computer-implemented method comprising:
storing, by a computing device of a computer and in a database accessible to the computing device, a set of pangenetic attributes of a set of individuals and a set of non-pangenetic attributes of the set of individuals, wherein the pangenetic attributes of the set are respectively and statistically associated with products via a set of statistical associations;
based on the set of statistical associations between the pangenetic attributes and the products, determining, by the computing device, product recommendations for a second set of individuals;
receiving, by the computing device and from the second set of individuals, a plurality of measures of satisfaction with the product recommendations;
based on the plurality of measures of satisfaction, learning, by the computing device, an association between (i) a set of core attributes comprising a subset of the pangenetic attributes and a subset of the non-pangenetic attributes, and (ii) a particular product of the products, wherein the set of core attributes are associated with the plurality of measures of satisfaction and the particular product;
storing, by the computing device and in the database, the learned association between the set of core attributes and the particular product, wherein the learned association provides a basis for subsequent recommendations of the particular product when a subsequent individual exhibits the subset of the pangenetic attributes;
receiving a representation of the subset of the pangenetic attributes;
storing, in the database and associated with a particular individual, the representation of the subset of the pangenetic attributes;
receiving a request for a product recommendation for the particular individual; and
in response to the subset of the pangenetic attributes being associated with the particular individual and the request for the product recommendation, providing a recommendation of the particular product.
2. The computer-implemented method of claim 1 , wherein the subset of the pangenetic attributes is one or more single nucleotide polymorphisms (SNPs).
3. The computer-implemented method of claim 1 , wherein the measures of satisfaction are from an ordered scale of two or more values.
4. The computer-implemented method of claim 1 , wherein the subset of the pangenetic attributes are associated with a phenotype, and wherein one or more of the measures of satisfaction indicate that the particular product is favorable to individuals exhibiting the phenotype.
5. The computer-implemented method of claim 1 , wherein the measures of satisfaction are stored in a two-dimensional item feedback matrix that maps instances of the measures of satisfaction from specific individuals to specific products.
6. The computer-implemented method of claim 1 , further comprising:
based on the measures of satisfaction, identifying a first individual of the second set of individuals and a second individual of the second set of individuals as a pangenetic cluster; and
predicting a preference of the second individual for the particular product based on a measure of satisfaction that the first individual has related to the particular product.
7. The computer-implemented method of claim 1 , wherein one or more of the set of pangenetic attributes are stored in a masked fashion to prevent access by unauthorized parties.
8. A computer-implemented method comprising:
receiving, by a computing device of a computer, a request related to a particular individual, wherein a database accessible to the computing device stores: (i) a set of pangenetic attributes of a set of individuals, the pangenetic attributes of the set respectively and statistically associated with products, (ii) a set of non-pangenetic attributes of the set of individuals, and (iii) a learned association between a subset of the pangenetic attributes and a subset of the non-pangenetic attributes therein forming a set of core attributes, and a particular product of the products, the learned association based on a plurality of measures of satisfaction with product recommendations that were received from the set of individuals, wherein the request includes a representation of the subset of the pangenetic attributes;
storing, by the computing device and in the database, the representation of the subset of the pangenetic attributes as associated with the particular individual;
based on at least some of the set of pangenetic attributes and the plurality of measures of satisfaction, identifying that a second particular individual is in a pangenetic cluster with the particular individual;
predicting a preference of the particular individual for the particular product based on a measure of satisfaction that the second particular individual has related to the particular product;
receiving a request for a product recommendation for the particular individual; and
based on the preference as predicted and the request for the product recommendation, providing a recommendation of the particular product.
9. The computer-implemented method of claim 8 , wherein the measures of satisfaction are from an ordered scale of two or more values.
10. The computer-implemented method of claim 8 , wherein the measures of satisfaction are stored in a two-dimensional item feedback matrix that maps instances of the measure of satisfaction from specific individuals to specific products.
11. A non-transitory computer-readable medium containing program instructions that, when executed by a processor of a computing device, cause the computing device to perform operations comprising:
storing, in a database accessible to the computing device, a set of pangenetic attributes of a set of individuals, wherein the pangenetic attributes of the set are respectively and statistically associated with products via a set of statistical associations, and a set of non-pangenetic attributes of the set of individuals;
based on the set of statistical associations between the pangenetic attributes and the products, determining product recommendations for a second set of individuals;
receiving, from the second set of individuals, a plurality of measures of satisfaction with the product recommendations;
based on the plurality of measures of satisfaction, learning an association between a subset of the pangenetic attributes, a subset of the non-pangenetic attributes, and a particular product of the products, therein forming a set of core attributes, wherein the set of core attributes are associated with the plurality of measures of satisfaction and the particular product;
storing, in the database, the learned association, wherein the learned association provides a basis for subsequent recommendations of the particular product when a subsequent individual exhibits the subset of the pangenetic attributes;
receiving a representation of the subset of the pangenetic attributes;
storing, in the database and associated with a particular individual, the representation of the subset of the pangenetic attributes;
receiving a request for a product recommendation for the particular individual; and
in response to the subset of the pangenetic attributes being associated with the particular individual and the request for the product recommendation, providing a recommendation of the particular product.
12. The non-transitory computer-readable medium of claim 11 , wherein the subset of the pangenetic attributes is one or more single nucleotide polymorphisms (SNPs).
13. The non-transitory computer-readable medium of claim 11 , wherein the measures of satisfaction are from an ordered scale of two or m ore values.
14. The non-transitory computer-readable medium of claim 11 , wherein the subset of the pangenetic attributes are associated with a phenotype, and wherein one or more of the measures of satisfaction indicate that the particular product is favorable to individuals exhibiting the phenotype.
15. The non-transitory computer-readable medium of claim 11 , wherein the measures of satisfaction are stored in a two-dimensional item feedback matrix that maps instances of the measures of satisfaction from specific individuals to specific products.
16. The non-transitory computer-readable medium of claim 11 , the operations further comprising:
based on the measures of satisfaction, identifying a first individual of the second set of individuals and a second individual of the second set of individuals as a pangenetic cluster; and
predicting a preference of the second individual for the particular product based on a measure of satisfaction that the first individual has related to the particular product.
17. The non-transitory computer-readable medium of claim 11 , wherein one or more of the set of pangenetic attributes are stored in a masked fashion to prevent access by unauthorized parties.