US 2025/0028980 A1Published application

Machine learning techniques for feature prediction based on clustering using ancillary and location data

AssigneeUnitedHealth Group Incorporated

InventorsKurt Johnson, Chiranjeev Pahuja, Krishna Naveen Kumar Kamatam, Elena Li

Life of this patent

Estimating the term…

Loading patent…

Abstract

Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for a predictive data analysis system that is configured to rank one or more candidate entities. A machine learning model is trained to rank the one or more candidate entities for initiating the performance of one or more prediction-based actions based on one or more sets of a plurality of clusters generated based on population data merged with ancillary data, and an association of location data with external domain data. The plurality of clusters is generated by generating embeddings for one or more features associated with a plurality of entities selected for clustering and determining a similarity score for entity pairs selected from the plurality of entities based on a distance function and the embeddings.

Claims20

Dependent claims

A computer-implemented method comprising:

merging, by one or more processors, population data with ancillary data from a first ancillary dataset and a second ancillary dataset, wherein (i) the population data has been extracted from a population dataset, and (ii) the populating dataset comprises location and feature information associated with a plurality of entities;
generating, by the one or more processors, location data associated with the plurality of entities based on the merged population data;
associating, by the one or more processors, the location data with external domain data;
determining, by the one or more processors, a plurality of distances between the plurality of entities based on the location data;
generating, by the one or more processors, one or more sets of a plurality of clusters comprising respective ones of the plurality of entities, wherein (i) one of the one or more sets of the plurality of clusters is generated based on respective ones of the plurality of distances associated with the respective ones of the plurality of entities are within a relative distance boundary, (ii) the respective ones of the plurality of entities comprises a first set of shared features or a second set of shared features, the first set of shared features and the second set of shared features determined based on (a) the merged population data, and (b) the association of the location data with the external domain data, and (iii) the one or more sets of the plurality of clusters is usable to train a prediction machine learning model to rank one or more candidate entities;
and
initiating, by the one or more processors, the performance of one or more prediction-based actions based on the ranking of the one or more candidate entities.

4 more elements

A computing apparatus comprising memory and one or more processors communicatively coupled to the memory, the one or more processors configured to:

merge population data with ancillary data from a first ancillary dataset and a second ancillary dataset, wherein (i) the population data has been extracted from a population dataset, and (ii) the populating dataset comprises location and feature information associated with a plurality of entities;
generate location data associated with the plurality of entities based on the merged population data;
associate the location data with external domain data;
determine a plurality of distances between the plurality of entities based on the location data;
generate one or more sets of a plurality of clusters comprising respective ones of the plurality of entities, wherein (i) one of the one or more sets of the plurality of clusters is generated based on respective ones of the plurality of distances associated with the respective ones of the plurality of entities are within a relative distance boundary, (ii) the respective ones of the plurality of entities comprises a first set of shared features or a second set of shared features, the first set of shared features and the second set of shared features determined based on (a) the merged population data, and (b) the association of the location data with the external domain data, and (iii) the one or more sets of the plurality of clusters is usable to train a prediction machine learning model to rank one or more candidate entities;
and
initiate the performance of one or more prediction-based actions based on the ranking of the one or more candidate entities.

4 more elements

One or more non-transitory computer-readable storage media including instructions that, when executed by one or more processors, cause the one or more processors to:

merge population data with ancillary data from a first ancillary dataset and a second ancillary dataset, wherein (i) the population data has been extracted from a population dataset, and (ii) the populating dataset comprises location and feature information associated with a plurality of entities;
generate location data associated with the plurality of entities based on the merged population data;
associate the location data with external domain data;
determine a plurality of distances between the plurality of entities based on the location data;
generate one or more sets of a plurality of clusters comprising respective ones of the plurality of entities, wherein (i) one of the one or more sets of the plurality of clusters is generated based on respective ones of the plurality of distances associated with the respective ones of the plurality of entities are within a relative distance boundary, (ii) the respective ones of the plurality of entities comprises a first set of shared features or a second set of shared features, the first set of shared features and the second set of shared features determined based on (a) the merged population data, and (b) the association of the location data with the external domain data, and (iii) the one or more sets of the plurality of clusters is usable to train a prediction machine learning model to rank one or more candidate entities;
and
initiate the performance of one or more prediction-based actions based on the ranking of the one or more candidate entities.

4 more elements

Dependencies are inferred from the claim text.