Temporally dynamic location-based predictive data analysis
AssigneeUnitedHealth Group Incorporated
InventorsAlison R. Stroh, Mario M. Suarez, Stephen R. Dion, Jordan R. DiPascal, Derek J. Syverson
Life of this patent
Estimating the term…
Abstract
Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing temporally dynamic location-based predictive data analysis. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform temporally dynamic location-based predictive data analysis by using at least one of cohort generation machine learning models and cohort-based growth forecast machine learning models.
Claims20
1- A computer-implemented method for performing temporally dynamic location-based predictive data analysis for an input locality data object given an input control policy data object, the computer-implemented method comprising:
- generating, using one or more processors and by using a cohort generation machine learning model, a locality cohort for the input locality data object and the input control policy data object, wherein:
- the locality cohort comprises one or more cohort locality data objects,
- each cohort locality data object of the one or more cohort locality data objects is associated with:
- (i) the input control policy data object, (ii) a corresponding cohort locality sentiment designation with respect to the input control policy data object, and (iii) a corresponding cohort locality adherence designation with respect to the input control policy data object,
- each corresponding cohort locality sentiment designation corresponds to a corresponding input locality sentiment designation for the input locality data object with respect to the input control policy data object, and
- each corresponding cohort locality adherence designation corresponds to a corresponding input locality adherence designation for the input locality data object with respect to the input control policy data object;
- generating, using the one or more processors and by using a cohort-based growth forecast machine learning model, an inferred cross-temporal growth prediction for the input locality data object with respect to the input control policy data object and in relation to a plurality of policy-indexed temporal units, wherein the cohort-based growth forecast machine learning model is configured to process a ground-truth cross-temporal growth data object for each cohort locality data object of the one or more cohort locality data objects in relation to the plurality of policy-indexed temporal units to generate the inferred cross-temporal growth prediction;
- and
- performing, using the one or more processors, one or more prediction-based actions based at least in part on the inferred cross-temporal growth prediction.
2- The computer-implemented method of claim 1, wherein each policy-indexed temporal unit of the plurality of policy-indexed temporal units is defined in accordance with a temporal offset period with respect to an adaptation timestamp for the input control policy data object.
3- The computer-implemented method of claim 1, wherein:
- the inferred cross-temporal growth prediction comprises a plurality of inferred temporal growth predictions,
- each inferred temporal growth prediction of the plurality of inferred temporal growth predictions is associated with a policy-indexed temporal unit of the plurality of policy-indexed temporal units,
- each ground-truth cross-temporal growth data object for a cohort locality data object of the one or more cohort locality data objects comprises a plurality of ground-truth temporal growth feature values, and
- each ground-truth temporal growth feature value of the plurality of ground-truth temporal growth feature values for a cohort locality data object of the one or more cohort locality data objects is associated with a policy-indexed temporal unit of the plurality of policy-indexed temporal units.
4- The computer-implemented method of claim 3, wherein generating the inferred cross-temporal growth prediction comprises:
- for each policy-indexed temporal unit of the plurality of policy-indexed temporal units, processing each ground-truth cross-temporal growth data object of the plurality of ground-truth cross-temporal predictions for a cohort locality data object of the one or more cohort locality data objects that is associated with the policy-indexed temporal unit using the cohort-based growth forecast machine learning model to generate the inferred temporal growth prediction of the plurality of inferred temporal growth predictions that is associated with the policy-indexed temporal unit;
- and
- determining the inferred cross-temporal growth prediction based at least in part on each inferred temporal growth prediction for a policy-indexed temporal unit of the plurality of policy-indexed temporal units.
5- The computer-implemented method of claim 3, wherein generating the inferred cross-temporal growth prediction comprises:
- for each input policy-indexed temporal unit of the plurality of policy-indexed temporal units,
- identifying a predecessor subset for the input policy-indexed temporal unit that comprises the input policy-indexed temporal unit and each policy-indexed temporal unit of the plurality of policy-indexed temporal unit that temporally precedes the input policy-indexed temporal unit, and
- processing each ground-truth cross-temporal growth data object of the plurality of ground-truth cross-temporal predictions for a cohort locality data object of the one or more cohort locality data objects that is in the predecessor subset for the input policy-indexed temporal unit using the cohort-based growth forecast machine learning model to generate the inferred temporal growth prediction of the plurality of inferred temporal growth predictions that is associated with the input policy-indexed temporal unit;
- and
- determining the inferred cross-temporal growth prediction based at least in part on each inferred temporal growth prediction for a policy-indexed temporal unit of the plurality of policy-indexed temporal units.
6- The computer-implemented method of claim 6, wherein the cohort-based growth forecast machine learning model is a sequential processing machine learning model.
7- The computer-implemented method of claim 1, wherein:
- the input locality data object is associated with one or more input locality demographic features,
- each cohort locality data object of the one or more of cohort locality data objects is associated with one or more cohort locality demographic features, and
- each one or more cohort locality demographic features for a cohort locality data object of the one or more of cohort locality data objects corresponds to the one or more input locality demographic features.
8- The computer-implemented method of claim 1, wherein performing the one or more prediction-based actions comprises:
- generating a prediction output user interface data object, wherein:
- (i) the prediction output user interface data object is configured to describe a prediction output user interface;
- (ii) the prediction output user interface is configured to:
- (a) enable updating the input locality data object from a plurality of candidate input locality data objects comprising the input locality data object and the one or more cohort locality data objects, and (b) describe a historical growth trend for the input locality data object and a projected growth trend for the input locality data object using a graph-based user interface element;
- and (iii) the projected growth trend is determined based at least in part on the inferred cross-temporal growth prediction for the input locality data object.
9- The computer-implemented method of claim 8, wherein the prediction output user interface is configured to enable updating the input control policy data object.
10- The computer-implemented method of claim 8, wherein the prediction output user interface is configured to enable updating the input locality sentiment designation.
11- The computer-implemented method of claim 8, wherein the prediction output user interface is configured to enable updating the input locality adherence designation.
12- The computer-implemented method of claim 8, wherein performing the one or more prediction-based actions further comprises providing the prediction output user interface data object to a client computing entity.
13- An apparatus for performing temporally dynamic location-based predictive data analysis for an input locality data object given an input control policy data object, the apparatus comprising at least one processor and at least one memory including program code, the at least one memory and the program code configured to, with the processor, cause the apparatus to at least:
- generate, by using a cohort generation machine learning model, a locality cohort for the input locality data object and the input control policy data object, wherein:
- the locality cohort comprises one or more cohort locality data objects,
- each cohort locality data object of the one or more cohort locality data objects is associated with:
- (i) the input control policy data object, (ii) a corresponding cohort locality sentiment designation with respect to the input control policy data object, and (iii) a corresponding cohort locality adherence designation with respect to the input control policy data object,
- each corresponding cohort locality sentiment designation corresponds to a corresponding input locality sentiment designation for the input locality data object with respect to the input control policy data object, and
- each corresponding cohort locality adherence designation corresponds to a corresponding input locality adherence designation for the input locality data object with respect to the input control policy data object;
- generate, by using a cohort-based growth forecast machine learning model, an inferred cross-temporal growth prediction for the input locality data object with respect to the input control policy data object and in relation to a plurality of policy-indexed temporal units, wherein the cohort-based growth forecast machine learning model is configured to process a ground-truth cross-temporal growth data object for each cohort locality data object of the one or more cohort locality data objects in relation to the plurality of policy-indexed temporal units to generate the inferred cross-temporal growth prediction;
- and
- perform one or more prediction-based actions based at least in part on the inferred cross-temporal growth prediction.
14- The apparatus of claim 13, wherein:
- the inferred cross-temporal growth prediction comprises a plurality of inferred temporal growth predictions,
- each inferred temporal growth prediction of the plurality of inferred temporal growth predictions is associated with a policy-indexed temporal unit of the plurality of policy-indexed temporal units,
- each ground-truth cross-temporal growth data object for a cohort locality data object of the one or more cohort locality data objects comprises a plurality of ground-truth temporal growth feature values, and
- each ground-truth temporal growth feature value of the plurality of ground-truth temporal growth feature values for a cohort locality data object of the one or more cohort locality data objects is associated with a policy-indexed temporal unit of the plurality of policy-indexed temporal units.
15- The apparatus of claim 14, wherein generating the inferred cross-temporal growth prediction comprises:
- for each policy-indexed temporal unit of the plurality of policy-indexed temporal units, processing each ground-truth cross-temporal growth data object of the plurality of ground-truth cross-temporal predictions for a cohort locality data object of the one or more cohort locality data objects that is associated with the policy-indexed temporal unit using the cohort-based growth forecast machine learning model to generate the inferred temporal growth prediction of the plurality of inferred temporal growth predictions that is associated with the policy-indexed temporal unit;
- and
- determining the inferred cross-temporal growth prediction based at least in part on each inferred temporal growth prediction for a policy-indexed temporal unit of the plurality of policy-indexed temporal units.
16- The apparatus of claim 14, wherein generating the inferred cross-temporal growth prediction comprises:
- for each input policy-indexed temporal unit of the plurality of policy-indexed temporal units,
- identifying a predecessor subset for the input policy-indexed temporal unit that comprises the input policy-indexed temporal unit and each policy-indexed temporal unit of the plurality of policy-indexed temporal unit that temporally precedes the input policy-indexed temporal unit, and
- processing each ground-truth cross-temporal growth data object of the plurality of ground-truth cross-temporal predictions for a cohort locality data object of the one or more cohort locality data objects that is in the predecessor subset for the input policy-indexed temporal unit using the cohort-based growth forecast machine learning model to generate the inferred temporal growth prediction of the plurality of inferred temporal growth predictions that is associated with the input policy-indexed temporal unit;
- and
- determining the inferred cross-temporal growth prediction based at least in part on each inferred temporal growth prediction for a policy-indexed temporal unit of the plurality of policy-indexed temporal units.
17- The apparatus of claim 13, wherein performing the one or more prediction-based actions comprises:
- generating a prediction output user interface data object, wherein:
- (i) the prediction output user interface data object is configured to describe a prediction output user interface;
- (ii) the prediction output user interface is configured to:
- (a) enable updating the input locality data object from a plurality of candidate input locality data objects comprising the input locality data object and the one or more cohort locality data objects, and (b) describe a historical growth trend for the input locality data object and a projected growth trend for the input locality data object using a graph-based user interface element;
- and (iii) the projected growth trend is determined based at least in part on the inferred cross-temporal growth prediction for the input locality data object.
18- A computer program product for performing temporally dynamic location-based predictive data analysis for an input locality data object given an input control policy data object, the computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions configured to
- generate, by using a cohort generation machine learning model, a locality cohort for the input locality data object and the input control policy data object, wherein:
- the locality cohort comprises one or more cohort locality data objects,
- each cohort locality data object of the one or more cohort locality data objects is associated with:
- (i) the input control policy data object, (ii) a corresponding cohort locality sentiment designation with respect to the input control policy data object, and (iii) a corresponding cohort locality adherence designation with respect to the input control policy data object,
- each corresponding cohort locality sentiment designation corresponds to a corresponding input locality sentiment designation for the input locality data object with respect to the input control policy data object, and
- each corresponding cohort locality adherence designation corresponds to a corresponding input locality adherence designation for the input locality data object with respect to the input control policy data object;
- generate, by using a cohort-based growth forecast machine learning model, an inferred cross-temporal growth prediction for the input locality data object with respect to the input control policy data object and in relation to a plurality of policy-indexed temporal units, wherein the cohort-based growth forecast machine learning model is configured to process a ground-truth cross-temporal growth data object for each cohort locality data object of the one or more cohort locality data objects in relation to the plurality of policy-indexed temporal units to generate the inferred cross-temporal growth prediction;
- and
- perform one or more prediction-based actions based at least in part on the inferred cross-temporal growth prediction.
19- The computer program product of claim 18, wherein:
- the inferred cross-temporal growth prediction comprises a plurality of inferred temporal growth predictions,
- each inferred temporal growth prediction of the plurality of inferred temporal growth predictions is associated with a policy-indexed temporal unit of the plurality of policy-indexed temporal units,
- each ground-truth cross-temporal growth data object for a cohort locality data object of the one or more cohort locality data objects comprises a plurality of ground-truth temporal growth feature values, and
- each ground-truth temporal growth feature value of the plurality of ground-truth temporal growth feature values for a cohort locality data object of the one or more cohort locality data objects is associated with a policy-indexed temporal unit of the plurality of policy-indexed temporal units.
20- The computer program product of claim 19, wherein generating the inferred cross-temporal growth prediction comprises:
- for each policy-indexed temporal unit of the plurality of policy-indexed temporal units, processing each ground-truth cross-temporal growth data object of the plurality of ground-truth cross-temporal predictions for a cohort locality data object of the one or more cohort locality data objects that is associated with the policy-indexed temporal unit using the cohort-based growth forecast machine learning model to generate the inferred temporal growth prediction of the plurality of inferred temporal growth predictions that is associated with the policy-indexed temporal unit;
- and
- determining the inferred cross-temporal growth prediction based at least in part on each inferred temporal growth prediction for a policy-indexed temporal unit of the plurality of policy-indexed temporal units.