Privacy-safe attribution data hub

    公开(公告)号:US11087027B2

    公开(公告)日:2021-08-10

    申请号:US16158344

    申请日:2018-10-12

    发明人: Wister Walcott

    IPC分类号: G06F21/62 G06Q30/02

    摘要: In an embodiment, one or more ad data sets are received at a first processor. The ad data sets may be partially encoded or encrypted to prevent the processor from viewing certain visitor information. The ad data sets are merged together around common users or order IDs. An attribution credit is applied to each advertising event, creating an attribution data set. The data in the attribution data set is aggregated according to each advertising event, and based on the aggregated results, an advertising recommendation is calculated and sent to the advertising entity.

    Audience definition for advertising systems

    公开(公告)号:US10360589B1

    公开(公告)日:2019-07-23

    申请号:US14657351

    申请日:2015-03-13

    IPC分类号: G06Q30/02 G05B19/418

    摘要: An ad facilitation server receives a definition of an audience from an advertiser, the definition expressed in terms of a URL that audience members have visited, such as a regular expression for URLs. Upon receiving a URL corresponding to a visit of a visitor to a page of the advertiser, the ad facilitation server determines whether the URL matches the audience definition provided earlier; if so, the ad facilitation server sends a request to a number of different ad publishers, requesting them to add the visitor to an associated audience. When an ad impression opportunity occurs on a particular ad publisher, the publisher considers bids previously submitted by the advertiser for the audience when selecting an ad for the ad impression opportunity. Thus, advertisers are enabled to bid on specific audiences defined by prior page visits, across a number of different ad publishers constituting different advertising channels.

    Continuous value-per-click estimation for low-volume terms

    公开(公告)号:US09311661B1

    公开(公告)日:2016-04-12

    申请号:US14018198

    申请日:2013-09-04

    IPC分类号: G06Q40/00 G06Q30/02

    摘要: An estimated conversion rate for a desired advertisement term is calculated. A total number of conversion events for terms having a conversion rate is determined for each of a plurality of conversion rates, and data is generated that describes a first distribution function representing the conversion rates and the associated numbers of conversion rates. Additionally, data describing a second distribution function representing the probability of a given number of conversion events occurring is also generated. Based at least in part on the first distribution function and the second distribution function, the estimated conversion rate for the desired advertisement term is computed.

    Continuous value-per-click estimation for low-volume terms
    4.
    发明授权
    Continuous value-per-click estimation for low-volume terms 有权
    针对小批量术语进行连续的每次点击评估

    公开(公告)号:US08583473B1

    公开(公告)日:2013-11-12

    申请号:US13348575

    申请日:2012-01-11

    IPC分类号: G06Q30/02

    摘要: An estimated conversion rate for a desired advertisement term is calculated. A total number of conversion events for terms having a conversion rate is determined for each of a plurality of conversion rates, and data is generated that describes a first distribution function representing the conversion rates and the associated numbers of conversion rates. Additionally, data describing a second distribution function representing the probability of a given number of conversion events occurring is also generated. Based at least in part on the first distribution function and the second distribution function, the estimated conversion rate for the desired advertisement term is computed.

    摘要翻译: 计算期望广告项的估计转换率。 针对多个转换率中的每一个确定具有转换率的术语的转换事件的总数,并且生成描述表示转换率和相关联的转换速率数的第一分布函数的数据。 此外,还产生描述表示给定数量的转换事件发生的概率的第二分布函数的数据。 至少部分地基于第一分配函数和第二分布函数,计算期望广告项的估计转换率。

    Private Computation of Multi-Touch Attribution

    公开(公告)号:US20240303690A1

    公开(公告)日:2024-09-12

    申请号:US18608238

    申请日:2024-03-18

    摘要: Anonymized data including multiple ad events is received at an attribution processor, along with a user ID and an ad ID. Each user ID has been anonymized with a one-way encryption key, and each ad ID has been anonymized with a two-way encryption key. A user ID and a customer value is received for a plurality of customers, the customer data being anonymized using the one-way encryption key for each user ID, and the two-way encryption key for each ad ID. Matching ad events are identified per conversion by comparing the user IDs in the encrypted ad data set to the user IDs in the encrypted customer data set. A customer value is then assigned to each ad event, and the customer values are summed for each ad ID across contributing events to create a converting ads data set. A recommendation is determined based on the summed values.

    Private Computation of Multi-Touch Attribution

    公开(公告)号:US20220405800A1

    公开(公告)日:2022-12-22

    申请号:US17895935

    申请日:2022-08-25

    IPC分类号: G06Q30/02 H04L9/08 G06F21/60

    摘要: A method comprises receiving an ad event data including data about a plurality of ad events, and including a user ID and an ad ID for each ad event in the ad event data set, where the ad event data set has been anonymized applying a one-way encryption key for each user ID in the ad event data set, and a two-way encryption key for the ad ID in the ad event data set. The attribution processor receives a customer data set including data about a plurality of customers, including a user ID and a customer value for each customer, where the customer data set has been anonymized using the one-way encryption key for each user ID in the data, and a private encryption key for the customer value. Without decrypting the received ad event data set and the received customer data set, the processor then matches ad events for each conversion by comparing the user IDs in the encrypted ad event data set to the user IDs in the encrypted customer data set to create a set of contributing ad events, assigns a share of the customer value to each relevant ad event, sums homomorphically the encrypted customer values for contributing events, and determines a recommendation for serving advertisements.

    Automated selection of bidders for online advertisements using collaborative bidding rules

    公开(公告)号:US10248973B1

    公开(公告)日:2019-04-02

    申请号:US14657675

    申请日:2015-03-13

    摘要: Approaches for collaborative advertising bidding comprise receiving, from an ad exchange, a bid request for an advertisement space for a viewing user. The approaches further comprise retrieving logged data associated with the viewing user, the logged data corresponding to the viewing user's online exposure to web content including at least one of commercial webpages, online representations of services or products having purchase information, and advertisements. A first advertiser and a second advertiser who have entered into an advertising collaborating relationship to respond to bid requests are identified. A determination is made as to whether a portion of the retrieved logged data for the viewing user is associated with the first advertiser or with the second advertiser. Additionally, based on the determining, one of the first advertiser and the second advertiser is selected to submit a bid for the advertisement space in response to the bid request.

    Continuous value-per-click estimation for low-volume terms
    8.
    发明授权
    Continuous value-per-click estimation for low-volume terms 有权
    针对小批量术语进行连续的每次点击评估

    公开(公告)号:US08117066B1

    公开(公告)日:2012-02-14

    申请号:US12170378

    申请日:2008-07-09

    IPC分类号: G06Q40/00

    摘要: An estimated conversion rate for a desired advertisement term is calculated. A total number of conversion events for terms having a conversion rate is determined for each of a plurality of conversion rates, and data is generated that describes a first distribution function representing the conversion rates and the associated numbers of conversion rates. Additionally, data describing a second distribution function representing the probability of a given number of conversion events occurring is also generated. Based at least in part on the first distribution function and the second distribution function, the estimated conversion rate for the desired advertisement term is computed.

    摘要翻译: 计算期望广告项的估计转换率。 针对多个转换率中的每一个确定具有转换率的术语的转换事件的总数,并且生成描述表示转换率和相关联的转换速率数的第一分布函数的数据。 此外,还产生描述表示给定数量的转换事件发生的概率的第二分布函数的数据。 至少部分地基于第一分配函数和第二分布函数,计算期望广告项的估计转换率。

    Private Computation of Multi-Touch Attribution

    公开(公告)号:US20210334408A1

    公开(公告)日:2021-10-28

    申请号:US17370256

    申请日:2021-07-08

    发明人: Wister Walcott

    IPC分类号: G06F21/62 G06Q30/02

    摘要: A plurality of anonymized publisher-user identifiers are received at a processor, and a plurality of anonymized advertiser-user identifiers are received from an advertiser at the processor. Without de-anonymizing any publisher-user identifiers in the received plurality of publisher-user identifiers and any advertiser-user identifiers in the received plurality of advertiser-user identifiers, the processor obliviously computes an intersection among the received publisher-user identifiers and the received ad-user identifiers to create an intersection set containing a plurality of advertiser-user identifiers matched with publisher-user identifiers.