Feature clustering of users, user correlation database access, and user interface generation system
View Patent ↗Methods, systems, and apparatus, including computer programs encoded on computer storage media, for a feature clustering of users, user correlation database access, and user interface generation system. The system can obtain information stored in different databases located across geographic regions, and determine unique users from the different information. The information can be included in unique records in the databases, with each record describing a particular user, and with each user described with imperfect identifying information. The system can analyze the different information utilizing machine learning models, and can associate each record with a particular unique user. The system can obtain identifications of items associated with each user, and determine the propensity of the user to disassociate with one or more items, or determine likelihoods of future association with different items not presently associated with the user.
1. A computerized method performed by one or more computer systems, wherein the computer systems are configured to access one or more electronic data sources in response to requests received from an interactive user interface, the method comprising:
obtaining, from the one or more electronic data sources each storing user records, information describing a plurality of users;
determining, using the obtained information, a plurality of unique users and user records associated with the unique users, wherein at least some user records associated with a particular unique user include at least some different information describing the particular user, and wherein user records associated with the particular unique user were stored in a plurality of electronic data sources, the electronic data sources storing user records according to differing formats;
obtaining, for each unique user and from associated user records, identifications of one or more services connected with the unique user and information describing one or more features of the unique user;
determining, for each unique user, information indicating likelihoods of the unique user disconnecting from one or more services connected with the unique user;
determining, for each unique user, one or more recommended services for the unique user comprising:
determining clusters to assign each unique user according to one or more features of respective unique users,
obtaining identifications of services connected with unique users that are included in a same cluster as the unique user and that are not connected with the unique user,
determining, based on popularities of the obtained services with respect to the cluster, one or more recommended services for the unique user; and
providing, for presentation in an interactive user interface, summary data describing one or more unique users.
2. The method of claim 1 , wherein determining a particular unique user comprises:
determining that a plurality of user records, obtained from the one or more databases, each describe the particular unique user.
3. The method of claim 2 , wherein each user record identifies a different spelling of a name associated with the particular unique user, and wherein determining that the plurality of user records each describes the particular unique user comprises:
determining, using identifying information included in the plurality of user records, that a likelihood that the user records are associated with the particular unique user exceeds a threshold.
4. The method of claim 2 , wherein a first user record of the plurality of user records does not include a name, and wherein determining that the plurality of user records each describes the particular unique user comprises:
determining, using identifying information other than a name included in the plurality of user records, that a likelihood that the first user record is associated with the particular user exceeds a threshold.
5. The method of claim 1 , wherein each user record identifies, at least, a name associated with a unique user, and one or more services connected with the unique user.
6. The method of claim 1 , wherein determining recommended services for a particular unique user comprises:
ordering services connected with unique users included in a same cluster as the particular unique user according to popularity of the service with respect to the cluster;
determining, based on the ordering, services which greater than a threshold percentage of unique users included in the same cluster are connected with and which the particular user is not connected with.
7. The method of claim 1 , further comprising:
receiving, from a user device, information identifying a particular unique user;
obtaining information describing the particular unique user, wherein the information comprises user churn information associated with the particular unique user and recommended services for the particular unique user; and
providing, for presentation in the interactive user interface, an identification of a service identified in the user churn information and an identification of a recommended service.
8. The method of claim 7 , further comprising:
providing, for presentation in the interactive user interface, analyses of descriptive text associated with interactions with the particular unique user, wherein the analyses indicate positive or negative interactions.
9. The method of claim 1 , further comprising:
receiving, from a user device, information identifying a particular cluster of a plurality of clusters, wherein each cluster is associated with particular unique users classified according to respective features of the particular unique users, and wherein the features are included in user records for each particular unique user; and
providing, for presentation in the interactive user interface, summary data of services associated with the particular unique users.
10. The method of claim 9 , wherein providing summary data of services associated with the particular unique users comprises:
providing, for presentation, identifications of one or more services that are recommended for the particular unique users at greater than a threshold percentage; and
providing a map of a geographic area that includes the particular unique users, wherein the map identifies concentrations of the particular unique users.
11. The method of claim 10 , further comprising:
receiving a selection of a particular recommended service; and
updating the map of the geographic region to include concentrations of one or more unique users of the particular unique users that are not connected with the selected recommended service.
12. A system comprising:
one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
obtaining, from one or more electronic data sources, information describing a plurality of users;
determining, using the obtained information, a plurality of unique users and user records associated with the unique users, wherein at least some user records associated with a particular unique user include at least some different information describing the particular unique user, and wherein user records associated with the particular unique user were stored in a plurality of electronic data sources, at least two electronic data sources storing user records according to differing formats;
obtaining, for each unique user and from associated user records, identifications of one or more services connected with the unique user and information describing one or more features of the unique user;
determining, for each unique user, information indicating likelihoods of the unique user disconnecting from one or more services connected with the unique user;
determining, for each unique user, one or more recommended services for the unique user comprising:
determining clusters to assign each unique user according to features of respective unique users,
obtaining identifications of services connected with unique users that are included in a same cluster as the unique user and that are not connected with the unique user,
determining, based on popularities of the obtained services with respect to the cluster, one or more recommended services for the unique user; and
providing, for presentation in an interactive user interface, summary data describing one or more unique users.
13. The system of claim 12 , wherein determining recommended services for a particular unique user comprises:
ordering services connected with unique users included in a same cluster as the particular unique user according to popularity of the service with respect to the cluster;
determining, based on the ordering, services which greater than a threshold percentage of unique users included in the same cluster are connected with and which the particular user is not connected with.
14. The system of claim 12 , wherein the operations further comprise:
receiving, from a user device, information identifying a particular unique user;
obtaining information describing the particular unique user, wherein the information comprises user churn information associated with the particular unique user and recommended services for the particular unique user; and
providing, for presentation in the interactive user interface, an identification of a service identified in the user churn information and an identification of a recommended service.
15. The system of claim 14 , wherein the operations further comprise:
providing, for presentation in the interactive user interface, analyses of descriptive text associated with interactions with the particular unique user, wherein the analyses indicate positive or negative interactions.
16. The system of claim 12 , wherein the operations further comprise:
receiving, from a user device, information identifying a particular cluster of a plurality of clusters, wherein each cluster is associated with particular unique users classified according to respective features of the particular unique users, and wherein the features are included in user records for each particular unique user; and
providing, for presentation in the interactive user interface, summary data of services associated with the particular unique users.
17. The system of claim 16 , wherein providing summary data of services associated with the particular unique users comprises:
providing, for presentation, identifications of one or more services that are recommended for the particular unique users at greater than a threshold percentage; and
providing a map of a geographic area that includes the particular unique users, wherein the map identifies concentrations of the particular unique users.
18. The system of claim 17 , wherein the operations further comprise:
receiving a selection of a particular recommended service; and
updating the map of the geographic region to include concentrations of one or more unique users of the particular unique users that are not connected with the selected recommended service.
19. The method of claim 1 , wherein determining recommended services for a particular unique user is further based on descriptive text included in user records associated with the particular unique user, the descriptive text informing respective likelihoods of the particular user connecting with services that the particular user is not connected with.
20. The system of claim 12 , wherein determining recommended services for a particular unique user is further based on descriptive text included in user records associated with the particular unique user, the descriptive text informing respective likelihoods of the particular user connecting with services that the particular user is not connected with.