公开(公告)号：US20180150874A1

公开(公告)日：2018-05-31

申请号：US15364999

申请日：2016-11-30

Applicant: Facebook, Inc.

Inventor： Zheng Chen ,  Shyamsundar Rajaram ,  Pradheep K. Elango

IPC: G06Q30/02 ,  G06N3/08

Abstract: An online system optimizes for longer attribution window conversions with an additive decomposition model by predicting the probability that a predefined action happens given an impression/click. The online system receives a content item from a content provider for display to a target user, and predicts a probability that a target user will convert given an interaction with the content item by the target user. The online system computes, by a first trained model, a short-term conversion probability of a conversion event happening within a first conversion window after the interaction. The online system computes, by a second trained model, a long-term conversion probability of the a conversion event happening within a second conversion window after the interaction, the second conversion window being longer than the first conversion window. The online system computes the conversion probability given the interaction based on the short-term conversion probability and the long-term conversion probability.

公开(公告)号：US11062360B1

公开(公告)日：2021-07-13

申请号：US15899581

申请日：2018-02-20

Applicant: Facebook, Inc.

Inventor： Raghavendra Rao Donamukkala ,  Zheng Chen ,  Toby Jonas F Roessingh ,  Shyamsundar Rajaram ,  Leon R Cho

IPC: G06Q30/02 ,  G06K9/62 ,  G06N20/00

Abstract: The present disclosure is directed toward systems and methods for optimizing view-through conversion rates. For example, systems and methods described herein train and utilize a machine learning model that predicts whether providing a digital impression to a particular networking system user will result in a conversion. Systems and methods described herein identify view-through conversions by generating a vector associated with the provision of a digital impression to a networking system user and receiving third-party conversion information during an attribution window. The systems and methods described herein then utilize the vector and conversion information to train the machine learning model to predict future conversions.

公开(公告)号：US10909569B1

公开(公告)日：2021-02-02

申请号：US16214114

申请日：2018-12-09

Applicant: Facebook, Inc.

Inventor： Nimish Rameshbhai Shah ,  Zheng Chen ,  Lixing Huang ,  Yang Li ,  Xin Liu

IPC: G06Q30/00 ,  G06Q30/02 ,  G06F16/901 ,  G06N20/00

Abstract: An online system obtains a composite prediction associated with a content item indicating a likelihood that a viewing user of the online system will perform a type of conversion associated with the content item via one or more paths of events leading to the type of conversion. The online system obtains the composite prediction based on a tree data structure describing the path(s) of events. Upon identifying an opportunity to present content to the viewing user, the online system identifies the tree data structure corresponding to the type of conversion from multiple tree data structures maintained in the online system and obtains a composite prediction associated with the content item by evaluating and performing operations associated with nodes of the tree data structure while traversing the nodes. The online system then determines whether to present the content item to the viewing user based on the composite prediction.

公开(公告)号：US10664866B2

公开(公告)日：2020-05-26

申请号：US15364999

申请日：2016-11-30

Applicant: Facebook, Inc.

Inventor： Zheng Chen ,  Shyamsundar Rajaram ,  Pradheep K. Elango

IPC: G06Q30/00 ,  G06Q30/02 ,  G06N20/20 ,  G06N5/00

Abstract: An online system optimizes for longer attribution window conversions with an additive decomposition model by predicting the probability that a predefined action happens given an impression/click. The online system receives a content item from a content provider for display to a target user, and predicts a probability that a target user will convert given an interaction with the content item by the target user. The online system computes, by a first trained model, a short-term conversion probability of a conversion event happening within a first conversion window after the interaction. The online system computes, by a second trained model, a long-term conversion probability of the a conversion event happening within a second conversion window after the interaction, the second conversion window being longer than the first conversion window. The online system computes the conversion probability given the interaction based on the short-term conversion probability and the long-term conversion probability.

公开(公告)号：US20190102784A1

公开(公告)日：2019-04-04

申请号：US15722126

申请日：2017-10-02

Applicant: Facebook, Inc.

Inventor： Zheng Chen ,  Robert Oliver Burns Zeldin ,  Shyamsundar Rajaram ,  Hao Song ,  Nimish Rameshbhai Shah

IPC: G06Q30/02

Abstract: A bidding system determines values for impression opportunities on an online system. Values are determined by a set of models. Each model of the set of models is associated with a user response and predicts the likelihood that the associated user response will occur following an impression. The models are ordered based on a predicted chronological ordering of user actions that lead towards a conversion. Each model is weighted based on its relevance to conversion and the accuracy of the model relative to the other models in the set of models. Predictions of the probability of user action generated by each model, as well as the model weights, are used to determine a value for impression opportunities. Data from impression opportunities are then used to further train the models and update the weights assigned to each model for use in determining values for subsequent impression opportunities.