公开(公告)号：US20190065638A1

公开(公告)日：2019-02-28

申请号：US15693326

申请日：2017-08-31

Applicant: Google Inc.

Inventor： Yunting Sun ,  Yuxue Jin ,  James Koehler ,  Xiaojing Huang ,  David Chan ,  Yueqing Wang ,  Conor Sontag ,  Shi Zhong ,  Luis Gonzalez Perez

IPC: G06F17/50 ,  G06F17/18

Abstract: Systems, methods, and computer-readable storage media that may be used to generate a Bayesian hierarchical model. One method includes generating a plurality of geographic regions by grouping one or more geographic sub-regions into each of the plurality of geographic regions. The method further includes receiving data for the geographic sub-regions, the data including responses, content inputs, content types, and location identifiers. The method further includes generating geo-level data from the received data by grouping the responses and content inputs of the received data based on a correlation of the location identifiers of the received data to the plurality of geographic regions. The method includes fitting a Bayesian hierarchical model based on at least the geo-level data, the content types, and the geographic regions and determining a content input mix for the content types for each geographic region based on the Bayesian hierarchical model and a content input constraint.

公开(公告)号：US20180308123A1

公开(公告)日：2018-10-25

申请号：US14056925

申请日：2013-10-17

Applicant: Google Inc.

Inventor： Shi Zhong ,  Robert Lee Marsa

IPC: G06Q30/02

CPC classification number: G06Q30/0246 ,  G06Q30/0273

Abstract: Embodiments disclosed provide new approaches for determining fractional attribution using aggregate advertising information. A channel weighting approach may derive the causal influence weight of any channel on conversions. In some embodiments, the approach may include arranging the conversion rate of each channel into different funnel stages, constructing aggregate-level data, and running a multi-stage regression computation using instrumental variables. This approach works with any number of different types of advertising channels, including online and offline channels, and provides the most accurate credit to each channel or sub-channel involved.

公开(公告)号：US10706191B2

公开(公告)日：2020-07-07

申请号：US15693326

申请日：2017-08-31

Applicant: Google Inc.

Inventor： Yunting Sun ,  Yuxue Jin ,  James Koehler ,  Xiaojing Huang ,  David Chan ,  Yueqing Wang ,  Conor Sontag ,  Shi Zhong ,  Luis Gonzalez Perez

IPC: H04N21/25 ,  G06F30/20 ,  G06F17/18 ,  H04L29/06 ,  G06T7/11 ,  G06Q30/02 ,  G06F111/10

Abstract: Systems, methods, and computer-readable storage media that may be used to generate a Bayesian hierarchical model. One method includes generating a plurality of geographic regions by grouping one or more geographic sub-regions into each of the plurality of geographic regions. The method further includes receiving data for the geographic sub-regions, the data including responses, content inputs, content types, and location identifiers. The method further includes generating geo-level data from the received data by grouping the responses and content inputs of the received data based on a correlation of the location identifiers of the received data to the plurality of geographic regions. The method includes fitting a Bayesian hierarchical model based on at least the geo-level data, the content types, and the geographic regions and determining a content input mix for the content types for each geographic region based on the Bayesian hierarchical model and a content input constraint.

公开(公告)号：US20160034948A1

公开(公告)日：2016-02-04

申请号：US14879714

申请日：2015-10-09

Applicant: Google Inc.

Inventor： Shi Zhong ,  Robert Lee Marsa

IPC: G06Q30/02

CPC classification number: G06Q30/0246 ,  G06Q30/0201

Abstract: Embodiments provide fractional attribution using aggregate-level information as well as user-level data. For example, aggregate data may be used to determine marginal conversion probabilities for individual attributes within each channel. For channels that have user-level data, the marginal conversion probabilities may be determined using user-level data associated with converted users and aggregate-level data associated with non-converting users. Different channels may have different attributes and the channels may be weighted, in one embodiment, via a causal analysis using instrumental variables. Each conversion path may be characterized by a set of attributes. Additionally, each conversion path may have touch points. The marginal conversion probabilities for the attributes may be combined to produce an importance weight for each touch point on a converting path. These importance weights can be normalized across the touch points on the converting path to obtain attribution results.

Abstract translation: 实施例使用聚合级别信息以及用户级数据提供分数归因。 例如，可以使用聚合数据来确定每个信道内的各个属性的边际转换概率。 对于具有用户级数据的信道，可以使用与转换的用户相关联的用户级数据和与非转换用户相关联的聚合级数据来确定边际转换概率。 在一个实施例中，不同的信道可以具有不同的属性，并且可以通过使用工具变量的因果分析来加权信道。 每个转换路径可以由一组属性来表征。 另外，每个转换路径可以具有接触点。 可以组合属性的边际转换概率以对转换路径上的每个接触点产生重要性权重。 这些重要权重可以在转换路径上的接触点上进行归一化，以获得归因结果。

公开(公告)号：US20160027041A1

公开(公告)日：2016-01-28

申请号：US14878759

申请日：2015-10-08

Applicant: Google Inc.

Inventor： Shi Zhong ,  Robert Lee Marsa

IPC: G06Q30/02 ,  H04L29/08

CPC classification number: G06Q30/0246 ,  H04L67/22

Abstract: Embodiments disclosed provide technical details on fractional attribution using online advertising information. More specifically, embodiments disclosed herein use historical data to determine one or more conditional probabilities and assign credit weights to given events. In this way, fairer and more accurate attribution of conversions to particular events may be assigned.

Abstract translation: 所公开的实施例提供了使用在线广告信息的分数归属的技术细节。 更具体地，本文公开的实施例使用历史数据来确定一个或多个条件概率并且将给定事件的信用权重分配。 以这种方式，可以分配更公平和更准确地将转换归因于特定事件。