DETERMINING USER-SPECIFIC HYPERPARAMETERS FOR DECISION SUPPORT MODELS

    公开(公告)号:US20240194341A1

    公开(公告)日:2024-06-13

    申请号:US18503486

    申请日:2023-11-07

    Applicant: Dexcom, Inc.

    CPC classification number: G16H50/20 G06N3/0985

    Abstract: Systems, devices, and methods for determining user-specific hyperparameters for decision support models are provided. In one embodiment, a non-transitory computer readable storage medium storing a program is provided, the program comprising instructions that, when executed by at least one processor of a computing device, cause the at least one processor to perform operations including performing an initial exploration phase; performing a training phase; and performing an exploration-exploitation phase by: dividing users into an exploration subset and an exploitation subset; determining at least one optimal hyperparameter for each user of the exploitation subset; determining, using the at least one optimal hyperparameter, at least one decision support output for each user of the exploitation subset; randomly assigning at least one hyperparameter to each user of the exploration subset; and determining, using the at least one randomly assigned hyperparameter, at least one decision support output for each user of the exploration subset.

    MACHINE LEARNING TECHNIQUES FOR OPTIMIZED COMMUNICATION WITH USERS OF A SOFTWARE APPLICATION

    公开(公告)号:US20230077948A1

    公开(公告)日:2023-03-16

    申请号:US17931531

    申请日:2022-09-12

    Applicant: Dexcom, Inc.

    Abstract: Certain aspects of the present disclosure relate to methods and systems for optimized delivery of communications including content to users of a software application. The method also includes obtaining, by a customer engagement platform (CEP), a set of cohort selection criteria for identifying a user cohort to deliver the content; identifying, by a data analytics platform (DAP), the user cohort to communicate with in accordance with the set of cohort selection criteria; identifying, by the DAP, one or more communication configurations for communicating with one or more sub-groups within the user cohort; and to each user of the user cohort, transmitting one or more communications based on the content and a corresponding communication configuration for a sub-group that may include the corresponding user; and measuring engagement outcomes associated with usage of the corresponding one or more communication configurations in communication with each of the sub-groups.

Patent Agency Ranking