AGGREGATE FEATURES FOR MACHINE LEARNING

    公开(公告)号:US20220382564A1

    公开(公告)日:2022-12-01

    申请号:US17819134

    申请日:2022-08-11

    申请人: Twitter, Inc.

    摘要: An example system includes a memory store of aggregate definitions. Each aggregate definition specifies a key value, a feature, a half-life value, and an aggregate operation metric to apply to a cross of the feature and the half-life value to generate aggregate metrics. The system also includes an aggregation engine that generates aggregate feature records from the input source based on the aggregate definitions and stores the aggregate feature records. An aggregate feature record includes an aggregate of the metric for the feature decayed over time using the half-life. The system also includes a query service that identifies, using the aggregate definitions, responsive aggregate feature records that satisfy parameters of a received request, applies the half-life to the responsive feature records, and provides the responsive feature records to a requester, the requester using the responsive feature records as input for a neural network.

    Overspend control in a messaging platform

    公开(公告)号:US11379436B1

    公开(公告)日:2022-07-05

    申请号:US16827630

    申请日:2020-03-23

    申请人: Twitter, Inc.

    摘要: A real-time messaging platform allows advertiser accounts to pay to insert candidate messages into the message streams requested by account holders. To accommodate multiple advertisers, the messaging platform controls an auction process that determines which candidate messages are selected for inclusion in a requested account holder's message stream. Selection is based on a bid for the candidate message, the message stream that is requested, and a variety of other factors that vary depending upon the implementation. The process for selection of candidate messages generally includes the following steps, though any given step may be omitted or combined into another step in a different implementation: targeting, filtering, prediction, ranking, and selection.

    Aggregate features for machine learning

    公开(公告)号:US10649794B2

    公开(公告)日:2020-05-12

    申请号:US15675671

    申请日:2017-08-11

    申请人: Twitter, Inc.

    摘要: An example system includes a memory store of aggregate definitions. Each aggregate definition specifies a key value, an output store, a feature, a half-life value, and an aggregate operation metric to apply to a cross of the feature and the half-life value to generate aggregate metrics. The system also includes an aggregation engine that generates aggregate feature records from the input source based on the aggregate definitions and stores the aggregate feature records in the output store. An aggregate feature record includes an aggregate of the metric for the feature decayed over time using the half-life. The system also includes a query service that identifies, using the aggregate definitions, responsive aggregate feature records that satisfy parameters of a received request, applies the half-life to the responsive feature records, and provides the responsive feature records to a requester, the requester using the responsive feature records as input for a neural network.

    Overspend control in a messaging platform

    公开(公告)号:US11409717B1

    公开(公告)日:2022-08-09

    申请号:US16827630

    申请日:2020-03-23

    申请人: Twitter, Inc.

    摘要: A real-time messaging platform allows advertiser accounts to pay to insert candidate messages into the message streams requested by account holders. To accommodate multiple advertisers, the messaging platform controls an auction process that determines which candidate messages are selected for inclusion in a requested account holder's message stream. Selection is based on a bid for the candidate message, the message stream that is requested, and a variety of other factors that vary depending upon the implementation. The process for selection of candidate messages generally includes the following steps, though any given step may be omitted or combined into another step in a different implementation: targeting, filtering, prediction, ranking, and selection.

    Temporal features in a messaging platform

    公开(公告)号:US10769677B1

    公开(公告)日:2020-09-08

    申请号:US15894550

    申请日:2018-02-12

    申请人: Twitter, Inc.

    摘要: A real-time messaging platform allows advertiser accounts to pay to insert candidate messages into the message streams requested by account holders. To accommodate multiple advertisers, the messaging platform controls an auction process that determines which candidate messages are selected for inclusion in a requested account holder's message stream. Selection is based on a bid for the candidate message, the message stream that is requested, and a variety of other factors that vary depending upon the implementation. The process for selection of candidate messages generally includes the following steps, though any given step may be omitted or combined into another step in a different implementation: targeting, filtering, prediction, ranking, and selection.

    Click-through prediction for targeted content

    公开(公告)号:US10657556B1

    公开(公告)日:2020-05-19

    申请号:US15178381

    申请日:2016-06-09

    申请人: Twitter, Inc.

    IPC分类号: G06Q30/02 G06N20/00

    摘要: In some examples, a computing device includes at least one processor and at least one module, operable by the at least one processor to receive, from a client device of a user, a request for one or more advertisements to display at the client device with a set of messages. The set of messages is associated with the user in a social network messaging service. The at least one module may be further operable to determine a probability that the user will select a candidate advertisement using a machine learning model based on point-wise learning and pair-wise learning. The at least one module may be further operable to determine, based on the probability that the user will select the candidate advertisement, a candidate score for the candidate advertisement, determine that the candidate score satisfies a threshold, and send, for display at the client device, the candidate advertisement.

    Click-through prediction for targeted content

    公开(公告)号:US11270333B1

    公开(公告)日:2022-03-08

    申请号:US16876565

    申请日:2020-05-18

    申请人: Twitter, Inc.

    IPC分类号: G06Q30/02 G06N20/00

    摘要: In some examples, a computing device includes at least one processor and at least one module, operable by the at least one processor to receive, from a client device of a user, a request for one or more advertisements to display at the client device with a set of messages. The set of messages is associated with the user in a social network messaging service. The at least one module may be further operable to determine a probability that the user will select a candidate advertisement using a machine learning model based on point-wise learning and pair-wise learning. The at least one module may be further operable to determine, based on the probability that the user will select the candidate advertisement, a candidate score for the candidate advertisement, determine that the candidate score satisfies a threshold, and send, for display at the client device, the candidate advertisement.

    Click-Through Prediction for Targeted Content

    公开(公告)号:US20210110428A1

    公开(公告)日:2021-04-15

    申请号:US17130495

    申请日:2020-12-22

    申请人: Twitter, Inc.

    IPC分类号: G06Q30/02 G06N20/00

    摘要: In some examples, a computing device includes at least one processor and at least one module, operable by the at least one processor to receive, from a client device of a user, a request for one or more advertisements to display at the client device with a set of messages. The set of messages is associated with the user in a social network messaging service. The at least one module may be further operable to determine a probability that the user will select a candidate advertisement using a machine learning model based on point-wise learning and pair-wise learning. The at least one module may be further operable to determine, based on the probability that the user will select the candidate advertisement, a candidate score for the candidate advertisement, determine that the candidate score satisfies a threshold, and send, for display at the client device, the candidate advertisement.

    Real time messaging platform
    9.
    发明授权

    公开(公告)号:US10769661B1

    公开(公告)日:2020-09-08

    申请号:US14214489

    申请日:2014-03-14

    申请人: Twitter, Inc.

    IPC分类号: G06Q30/02

    摘要: A real-time messaging platform allows advertiser accounts to pay to insert candidate messages into the message streams requested by account holders. To accommodate multiple advertisers, the messaging platform controls an auction process that determines which candidate messages are selected for inclusion in a requested account holder's message stream. Selection is based on a bid for the candidate message, the message stream that is requested, and a variety of other factors that vary depending upon the implementation. The process for selection of candidate messages generally includes the following steps, though any given step may be omitted or combined into another step in a different implementation: targeting, filtering, prediction, ranking, and selection.

    Temporal features in a messaging platform
    10.
    发明授权
    Temporal features in a messaging platform 有权
    消息平台中的时态特征

    公开(公告)号:US09117227B1

    公开(公告)日:2015-08-25

    申请号:US14214523

    申请日:2014-03-14

    申请人: Twitter, Inc.

    IPC分类号: G06F17/30 G06F7/00 G06Q30/02

    摘要: A real-time messaging platform allows advertiser accounts to pay to insert candidate messages into the message streams requested by account holders. To accommodate multiple advertisers, the messaging platform controls an auction process that determines which candidate messages are selected for inclusion in a requested account holder's message stream. Selection is based on a bid for the candidate message, the message stream that is requested, and a variety of other factors that vary depending upon the implementation. The process for selection of candidate messages generally includes the following steps, though any given step may be omitted or combined into another step in a different implementation: targeting, filtering, prediction, ranking, and selection.

    摘要翻译: 实时消息平台允许广告客户支付将候选消息插入到账户所要求的消息流中。 为了容纳多个广告商,消息收发平台控制拍卖过程,确定哪些候选消息被选择以包含在所请求的账户持有者的消息流中。 选择是基于候选消息的出价,请求的消息流以及根据实现而变化的各种其他因素。 用于选择候选消息的过程通常包括以下步骤,尽管任何给定的步骤可以被省略或组合到不同实现中的另一步骤:目标,过滤,预测,排序和选择。