Machine learning techniques for generating recalculation determinations for predicted risk scores

Patent metadata

Field	Value
Publication number	US-2022327404-A1
Application number	US-202117382691-A
Country	US
Kind code	A1
Filing date	Jul 22, 2021
Priority date	Apr 9, 2021
Publication date	Oct 13, 2022
Grant date	—

Abstract

Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing risk score generation predictive data analysis. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform risk score generation predictive data analysis by utilizing at least one of event-based confidence scores and delay-based confidence scores.

First claim

1 . A computer-implemented method for determining a recalculation determination for a predicted risk score that is associated with a target risk category with respect to a target temporal unit, the computer-implemented method comprising:
determining, using a processor and based at least in part on a recalculation delay value for a recalculation delay period that is associated with the target temporal unit, a delay-based confidence score for the target temporal unit, wherein: (i) the recalculation delay value is determined based at least in part on a calculation temporal unit timestamp for the predicted risk score and a target temporal unit timestamp for the target temporal unit, and (ii) the delay-based confidence score is determined based at least in part on a delay-based confidence scoring reduction scheme for the target risk category; determining, using the processor and based at least in part on one or more recalculation delay period events associated with the recalculation delay period, an event-based confidence score for the target temporal unit; determining, using the processor, a hybrid confidence score for the predicted risk score based at least in part on the delay-based confidence score and the event-based confidence score; determining, using the processor, the recalculation determination based at least in part on whether the hybrid confidence score satisfies a hybrid confidence score threshold; performing, using the processor, one or more prediction-based actions based at least in part on the recalculation determination.

2 . The computer-implemented method of claim 1 , wherein determining the event-based confidence score comprises:
detecting the one or more recalculation delay period events associated with the recalculation delay period; for each recalculation delay period event, determining an event weight based at least in part on an event weighting scheme for the target risk category; and determining the event-based confidence score based at least in part on each event weighting scheme.

3 . The computer-implemented method of claim 2 , wherein detecting the one or more recalculation delay period events comprises:
determining an event graph data object for the recalculation delay period; determining, based at least in part on the event graph data object and using a graph-based machine learning model, one or more graph-based events for the recalculation delay period; and determining the one or more recalculation delay period events based at least in part on the one or more graph-based events.

4 . The computer-implemented method of claim 2 , wherein detecting the one or more recalculation delay period events comprises:
determining an event history data object for the recalculation delay period; determining, based at least in part on the event history data object, one or more history-based events for the recalculation delay period; and determining the one or more recalculation delay period events based at least in part on the one or more history-based events.

5 . The computer-implemented method of claim 2 , wherein determining the event weight for a particular recalculation delay period event comprises:
determining an initial event weight for the particular recalculation delay period event based at least in part on the event weighting scheme for the target risk category; determining an event weight adjustment value for the particular recalculation delay period based at least in part on a recalculation delay period event timestamp for the particular recalculation delay period event; and determining the event weight based at least in part on the initial event weight and the event weight adjustment value

6 . The computer-implemented method of claim 1 , wherein determining the hybrid confidence score comprises:
determining a delay-based confidence score weight and an event-based confidence score weight for the target risk category; determining an adjusted delay-based confidence score based at least in part on the delay-based confidence score and the delay-based confidence score weight; determining an adjusted event-based confidence score based at least in part on the event-based confidence score and the event-based confidence score weight; and determining the hybrid confidence score based at least in part on the adjusted delay-based confidence score and the adjusted event-based confidence score.

7 . The computer-implemented method of claim 1 , wherein performing the one or more prediction-based actions comprises:
in response to determining that the recalculation determination is an affirmative recalculation determination, determining a recalculated predicted risk score for the target risk category.

8 . An apparatus for determining a recalculation determination for a predicted risk score that is associated with a target risk category with respect to a target temporal unit, 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:
determine, based at least in part on a recalculation delay value for a recalculation delay period that is associated with the target temporal unit, a delay-based confidence score for the target temporal unit, wherein: (i) the recalculation delay value is determined based at least in part on a calculation temporal unit timestamp for the predicted risk score and a target temporal unit timestamp for the target temporal unit, and (ii) the delay-based confidence score is determined based at least in part on a delay-based confidence scoring reduction scheme for the target risk category; determine, based at least in part on one or more recalculation delay period events associated with the recalculation delay period, an event-based confidence score for the target temporal unit; determine a hybrid confidence score for the predicted risk score based at least in part on the delay-based confidence score and the event-based confidence score; determine the recalculation determination based at least in part on whether the hybrid confidence score satisfies a hybrid confidence score threshold; perform one or more prediction-based actions based at least in part on the recalculation determination.

9 . The apparatus of claim 8 , wherein determining the event-based confidence score comprises:
detecting the one or more recalculation delay period events associated with the recalculation delay period; for each recalculation delay period event, determining an event weight based at least in part on an event weighting scheme for the target risk category; and determining the event-based confidence score based at least in part on each event weighting scheme.

10 . The apparatus of claim 9 , wherein detecting the one or more recalculation delay period events comprises:
determining an event graph data object for the recalculation delay period; determining, based at least in part on the event graph data object and using a graph-based machine learning model, one or more graph-based events for the recalculation delay period; and determining the one or more recalculation delay period events based at least in part on the one or more graph-based events.

11 . The apparatus of claim 9 , wherein detecting the one or more recalculation delay period events comprises:
determining an event history data object for the recalculation delay period; determining, based at least in part on the event history data object, one or more history-based events for the recalculation delay period; and determining the one or more recalculation delay period events based at least in part on the one or more history-based events.

Assignees

• Optum Inc

Inventors

• Godden Paul J
• Mccreary Daniel George
• Boss Gregory J
• Megerian Mark Gregory

Classifications

• G06N20/00

  Machine learning · CPC title

• G06N5/02 Primary

  Knowledge representation; Symbolic representation · CPC title

• G06N5/04 Primary

  Inference or reasoning models · CPC title