TRAINING A MODEL TO PREDICT LIKELIHOODS OF USERS PERFORMING AN ACTION AFTER BEING PRESENTED WITH A CONTENT ITEM

    公开(公告)号:US20250095007A1

    公开(公告)日:2025-03-20

    申请号:US18967681

    申请日:2024-12-04

    Applicant: Maplebear Inc.

    Abstract: An online concierge system trains a user interaction model to predict a probability of a user performing an interaction after one or more content items are displayed to the user. This provides a measure of an effect of displaying content items to the user on the user performing one or more interactions. The user interaction model is trained from displaying content items to certain users of the online concierge system and withholding display of the content items to other users of the online concierge system. To train the user interaction model, the user interaction model is applied to labeled examples identifying a user and value based on interactions the user performed after one or more content items were displayed to the user and interactions the user performed when one or more content items were not used.

    Training a model to predict likelihoods of users performing an action after being presented with a content item

    公开(公告)号:US11593819B2

    公开(公告)日:2023-02-28

    申请号:US17343026

    申请日:2021-06-09

    Abstract: An online concierge system trains a user interaction model to predict a probability of a user performing an interaction after one or more content items are displayed to the user. This provides a measure of an effect of displaying content items to the user on the user performing one or more interactions. The user interaction model is trained from displaying content items to certain users of the online concierge system and withholding display of the content items to other users of the online concierge system. To train the user interaction model, the user interaction model is applied to labeled examples identifying a user and value based on interactions the user performed after one or more content items were displayed to the user and interactions the user performed when one or more content items were not used.

    TRAINING A MODEL TO PREDICT LIKELIHOODS OF USERS PERFORMING AN ACTION AFTER BEING PRESENTED WITH A CONTENT ITEM

    公开(公告)号:US20220398605A1

    公开(公告)日:2022-12-15

    申请号:US17343026

    申请日:2021-06-09

    Abstract: An online concierge system trains a user interaction model to predict a probability of a user performing an interaction after one or more content items are displayed to the user. This provides a measure of an effect of displaying content items to the user on the user performing one or more interactions. The user interaction model is trained from displaying content items to certain users of the online concierge system and withholding display of the content items to other users of the online concierge system. To train the user interaction model, the user interaction model is applied to labeled examples identifying a user and value based on interactions the user performed after one or more content items were displayed to the user and interactions the user performed when one or more content items were not used.

    Training a model to predict likelihoods of users performing an action after being presented with a content item

    公开(公告)号:US12198155B2

    公开(公告)日:2025-01-14

    申请号:US18112438

    申请日:2023-02-21

    Applicant: Maplebear Inc.

    Abstract: An online concierge system trains a user interaction model to predict a probability of a user performing an interaction after one or more content items are displayed to the user. This provides a measure of an effect of displaying content items to the user on the user performing one or more interactions. The user interaction model is trained from displaying content items to certain users of the online concierge system and withholding display of the content items to other users of the online concierge system. To train the user interaction model, the user interaction model is applied to labeled examples identifying a user and value based on interactions the user performed after one or more content items were displayed to the user and interactions the user performed when one or more content items were not used.

Patent Agency Ranking