公开(公告)号：US20180253651A1

公开(公告)日：2018-09-06

申请号：US15447068

申请日：2017-03-01

Applicant: Facebook, Inc.

Inventor： Andrew Donald Yates ,  Gunjit Singh ,  Kurt Dodge Runke

IPC: G06N5/02 ,  G06Q50/00 ,  G06N99/00

CPC classification number: G06N5/02 ,  G06N20/00 ,  G06Q50/01

Abstract: An online system generates predicted outcomes for a content distribution program that distributes content to users of the online system, the predicted outcome indicating a likelihood for the occurrence of an outcome of a content presentation. The online system transmits the one or more predicted outcomes to the third party system, and receives prediction improvement data from the third party system, the prediction improvement data indicating an adjustment to errors in the predicted outcomes based on a prediction by the third party system. The online system updates the properties of a content distribution program based on the prediction improvement data, the updated content distribution program causing the online system to generate new predicted outcomes based on the prediction improvement data in content presentation opportunities. The online system also transmits content to users of the online system based on the updated content distribution program.

公开(公告)号：US20180218410A1

公开(公告)日：2018-08-02

申请号：US15421397

申请日：2017-01-31

Applicant: Facebook, Inc.

Inventor： Ramnik Arora ,  Kurt Dodge Runke

IPC: G06Q30/02

CPC classification number: G06Q30/0275 ,  G06Q30/0242 ,  G06Q30/0267 ,  G06Q30/0277

Abstract: An online system presents ads on behalf of advertisers to users of the online system. For an ad campaign, the online system determines bid prices to be associated with an ad for different eligible users based at least on user cost models associated with the eligible users and a value curve that specifies an amount of value the advertiser derives from each ad impression. Using user cost models and the value curve, the online system evaluates how much value an advertiser will derive from ad impressions. The online system maximizes an expected value that an advertiser can derive from ad impressions to an eligible user to determine a bid price. The online system calculates an expected value as an amount of value that the advertiser derives from the ad impression with a bid price weighted by a likelihood of winning auctions with a bid price.

公开(公告)号：US11106997B2

公开(公告)日：2021-08-31

申请号：US15721203

申请日：2017-09-29

Applicant: Facebook, Inc.

Inventor： Andrew Donald Yates ,  Gunjit Singh ,  Kurt Dodge Runke

IPC: G06N5/04 ,  G06N20/00 ,  G06N3/08 ,  G06N3/04 ,  H04L29/08

Abstract: An online system uses multiple machine learning models to select content for providing to a user of the online system. Specifically, the online system trains a general model that intakes a first set of features and outputs predictions at a general level. The online system further trains a residual model that intakes a second set of features. The residual model predicts a residual (e.g., an error) of the predictions outputted by the general model. Therefore, the predicted residual from the residual model is combined with the prediction from the general model in order to correct for the over-generality of the general model. The online system may use the combined prediction to send content to users.

公开(公告)号：US10438232B2

公开(公告)日：2019-10-08

申请号：US15676928

申请日：2017-08-14

Applicant: Facebook, Inc.

Inventor： Andrew Donald Yates ,  Kurt Dodge Runke

IPC: G06Q30/02

Abstract: An online system determines how presenting an awareness campaign to a user will affect the user's likelihood of converting to a related direct response campaign. For the user, the online system creates a benchmark exposure profile representing the user's exposure history before the awareness campaign. Similarly, the online system determines the user's simulated exposure profile, which represents the user's brand exposure history after having been exposed to the awareness campaign. A response prediction for the direct response campaign is determined for the benchmark exposure profile and the simulated exposure profile. The online system estimates the difference between the response prediction and the simulated response prediction to determine a delivery control value of presenting the awareness campaign to a user. The delivery control value is used to determine an effective impression value for the awareness campaign and conversion value for the related direct response campaign.

公开(公告)号：US20190102693A1

公开(公告)日：2019-04-04

申请号：US15721189

申请日：2017-09-29

Applicant: Facebook, Inc.

Inventor： Andrew Donald Yates ,  Gunjit Singh ,  Kurt Dodge Runke

IPC: G06N99/00 ,  G06N7/00

Abstract: An online system determines candidate parameter values to be used by a machine learning algorithm to train a machine learning model by saving historical datasets that include historical parameter searches and the performance of prior machine learning models that were trained on the historical parameters. Using the historical datasets, the online system identifies parameter predictors associated with a relation between candidate parameter values and properties of the training dataset that will be used to train the machine learning model. The online system trains the machine learning models according to the candidate parameter values and validates that the machine learning model is performing as expected. If the online system detects that the machine learning model is performing outside of an acceptable range, the online system determines new candidate parameter values and re-trains the machine learning model.

公开(公告)号：US20180075367A1

公开(公告)日：2018-03-15

申请号：US15261746

申请日：2016-09-09

Applicant: Facebook, Inc.

Inventor： Andrew Donald Yates ,  Kurt Dodge Runke ,  Gunjit Singh

IPC: G06N99/00 ,  G06F17/30

CPC classification number: G06N20/00 ,  G06Q30/0269 ,  G06Q50/01

Abstract: An online system, such as a social networking system, generates shared models for one or more clusters of categories. A shared model for a cluster is common to the categories assigned to the cluster. In this manner, the shared models are specific to the group of categories (e.g., selected content providers) in each cluster while requiring a reasonable computational complexity for the online system. The categories are clustered based on the performance of a model specific to a category on data for other categories.