System for Genetic-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:
obtaining genetic attributes representing a plurality of individuals;
presenting, by way of a computer-mediated interface, a questionnaire to each of the individuals, wherein the questionnaire relates to health-related content;
receiving, by way of the computer-mediated interface, respective responses corresponding to the questionnaire from each of the individuals;
identifying patterns within the genetic attributes;
determining associations between the patterns within the genetic attributes of the individuals and their respective responses corresponding to the questionnaire;
determining, from the associations, correlations between the health-related content and the patterns within the genetic attributes;
based on the correlations between the health-related content and the patterns within the genetic attributes, clustering the individuals into groups; and
based on the correlations and the groups, making a recommendation regarding the health-related content to an individual of the plurality of individuals.
2 . The computer-implemented method of claim 1 , wherein making the recommendation regarding the health-related content to the individual comprises:
identifying a most similar group to the individual;
predicting, via the correlations between the health-related content and patterns within the genetic attributes of constituents of the most similar group, portions of the health-related content that may be suitable for the individual; and
using the prediction as a basis to recommend a subset of the health-related content to the individual.
3 . The computer-implemented method of claim 2 , wherein identifying the most similar group to the individual comprises:
computing aggregate similarity scores respectively between the individual and the groups;
determining a most similar aggregate similarity score to the individual within the aggregate similarity scores; and
associating the individual with the group that has a closest aggregate similarity score.
4 . The computer-implemented method of claim 1 , wherein clustering the individuals into groups further comprises:
computing a quantitative similarity score for each individual within each group;
identifying a similarity threshold for each group; and
clustering the individuals whose quantitative similarity scores exceed the similarity threshold into subgroups within their respective groups.
5 . The computer-implemented method of claim 1 , wherein the individual of the plurality of individuals has opted-in to using the genetic attributes to determine aspects of the health-related content relevant to the individual.
6 . The computer-implemented method of claim 1 , further comprising:
accessing genetic attributes of a further individual of the plurality of individuals;
determining, from the correlations, aspects of the health-related content relevant to the further individual; and
providing, to the further individual, the aspects of the health-related content relevant to the further individual.
7 . The computer-implemented method of claim 1 , further comprising:
receiving behavioral attributes of the plurality of individuals;
storing, in a further database structure, further associations between the genetic attributes of the individuals and their respective behavioral attributes;
based on the further associations between the genetic attributes of the individuals and their respective behavioral attributes, clustering the individuals into further groups; and
determining, from the further associations and the further groups, further correlations between the respective behavioral attributes and patterns within the genetic attributes, wherein making the recommendation is also based on the further correlations.
8 . The computer-implemented method of claim 1 , further comprising:
receiving physical attributes of the plurality of individuals;
storing, in a further database structure, further associations between the genetic attributes of the individuals and their respective physical attributes;
based on the further associations between the genetic attributes of the individuals and their respective physical attributes, clustering the individuals into further groups; and
determining, from the further associations and the further groups, further correlations between the respective physical attributes and patterns within the genetic attributes, wherein making the recommendation is also based on the further correlations.
9 . The computer-implemented method of claim 8 , wherein the physical attributes of the plurality of individuals comprise at least one of: gender, age, height, or weight.
10 . The computer-implemented method of claim 1 , further comprising:
receiving situational attributes of the plurality of individuals;
storing, in a further database structure, further associations between the situational attributes of the individuals and their respective responses corresponding to the questionnaire;
based on the further associations between the genetic attributes of the individuals and their respective situational attributes, clustering the individuals into further groups; and
determining, from the further associations and the further groups, further correlations between the respective situational attributes and the respective responses corresponding to the questionnaire, wherein making the recommendation is also based on the further correlations.
11 . The computer-implemented method of claim 10 , wherein the situational attributes of the plurality of individuals comprise at least one of: marital status, ethnicity, or home ZIP code.
12 . A non-transitory computer-readable medium storing program instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations comprising:
obtaining genetic attributes representing a plurality of individuals;
presenting, by way of a computer-mediated interface, a questionnaire to each of the individuals, wherein the questionnaire relates to health-related content;
receiving, by way of the computer-mediated interface, respective responses corresponding to the questionnaire from each of the individuals;
identifying patterns within the genetic attributes;
determining associations between the patterns within the genetic attributes of the individuals and their respective responses corresponding to the questionnaire;
determining, from the associations, correlations between the health-related content and the patterns within the genetic attributes;
based on the correlations between the health-related content and the patterns within the genetic attributes, clustering the individuals into groups; and
based on the correlations and the groups, making a recommendation regarding the health-related content to an individual of the plurality of individuals.
13 . The non-transitory computer-readable medium of claim 12 , wherein making the recommendation regarding the health-related content to the individual comprises:
identifying a most similar group to the individual;
predicting, via the correlations between the health-related content and patterns within the genetic attributes of constituents of the most similar group, portions of the health-related content that may be suitable for the individual; and
using the prediction as a basis to recommend a subset of the health-related content to the individual.
14 . The non-transitory computer-readable medium of claim 13 , wherein identifying the most similar group to the individual comprises:
computing aggregate similarity scores respectively between the individual and the groups;
determining a most similar aggregate similarity score to the individual within the aggregate similarity scores; and
associating the individual with the group that has the closest aggregate similarity score.
15 . The non-transitory computer-readable medium of claim 12 , wherein clustering the individuals into groups further comprises:
computing a quantitative similarity score for each individual within each group;
identifying a similarity threshold for each group; and
clustering the individuals whose quantitative similarity scores exceed the similarity threshold into subgroups within their respective groups.
16 . The non-transitory computer-readable medium of claim 12 , the operations further comprising:
accessing genetic attributes of a further individual of the plurality of individuals;
determining, from the correlations, aspects of the health-related content relevant to the further individual; and
providing, to the further individual, the aspects of the health-related content relevant to the further individual.
17 . The non-transitory computer-readable medium of claim 12 , the operations further comprising:
receiving behavioral attributes of the plurality of individuals;
storing, in a further database structure, further associations between the genetic attributes of the individuals and their respective behavioral attributes;
based on the further associations between the genetic attributes of the individuals and their respective behavioral attributes, clustering the individuals into further groups; and
determining, from the further associations and the further groups, further correlations between the respective behavioral attributes and patterns within the genetic attributes, wherein making the recommendation is also based on the further correlations.
18 . The non-transitory computer-readable medium of claim 12 , the operations further comprising:
receiving physical attributes of the plurality of individuals;
storing, in a further database structure, further associations between the genetic attributes of the individuals and their respective physical attributes;
based on the further associations between the genetic attributes of the individuals and their respective physical attributes, clustering the individuals into further groups; and
determining, from the further associations and the further groups, further correlations between the respective physical attributes and patterns within the genetic attributes, wherein making the recommendation is also based on the further correlations.
19 . The non-transitory computer-readable medium of claim 12 , the operations further comprising:
receiving situational attributes of the plurality of individuals;
storing, in a further database structure, further associations between the situational attributes of the individuals and their respective responses corresponding to the questionnaire;
based on the further associations between the genetic attributes of the individuals and their respective situational attributes, clustering the individuals into further groups; and
determining, from the further associations and the further groups, further correlations between the respective situational attributes and the respective responses corresponding to the questionnaire, wherein making the recommendation is also based on the further correlations.
20 . A computing system comprising:
one or more processors;
memory; and
program instructions, stored in the memory, that upon execution by the one or more processors cause the computing system to perform operations comprising:
obtaining genetic attributes representing a plurality of individuals;
presenting, by way of a computer-mediated interface, a questionnaire to each of the individuals, wherein the questionnaire relates to health-related content;
receiving, by way of the computer-mediated interface, respective responses corresponding to the questionnaire from each of the individuals;
identifying patterns within the genetic attributes;
determining associations between the patterns within the genetic attributes of the individuals and their respective responses corresponding to the questionnaire;
determining, from the associations, correlations between the health-related content and the patterns within the genetic attributes;
based on the correlations between the health-related content and the patterns within the genetic attributes, clustering the individuals into groups; and
based on the correlations and the groups, making a recommendation regarding the health-related content to an individual of the plurality of individuals.