Ooyala, Inc.

Facebook, Inc.

Nimrod Hoofien

Sean Michael Knapp

Harry J M Robertson

Caleb E Spare

Zhichen Xu

Robert William Cathcart

Lei Huang

Hong Ge

Sami Abu-El-Haija

A social networking system prices advertisements presented to a user of a social networking system via a client device in a state that provides the user with limited functionality by applying discount factors to bid amounts associated with advertisements selected for presentation. A discount factor is based on the likelihood of the user viewing or interacting with an advertisement via the social networking system presented while the client device is in the state providing the user with limited functionality. This likelihood is determined based on information including a history of user interaction with the client device and contextual information indicating whether the client device is in use.

Pricing advertisements presented by a client device in a limited functionality state

A system is provided that facilitates achieving a goal associated with a particular video asset. The system may provide an interface through which a user may specify control parameters that are to be the targets of testing, and a goal or combination of goals. The system may control a controller that performs experiments in an attempt to identify optimal values, relative to the specified goals, for the control parameters. The optimal values may be determined and tested on a per-individual-video asset basis. Further, the controller may generate multiple sets of optimal values for a given video, where each set is associated with a different combination of request attributes. To estimate the optimal parameter values for one video, the controller may use usage information collected for that video, as well as usage information collected for similar videos.

Goal-based video delivery system

Techniques are provided for selecting which videos to recommend to users by predicting the degree to which recommending each video will satisfy certain goals. To make the predictions, a trained machine learning engine is fed both collaborative filtering parameter values and content-based filtering parameter values. In the case of video-to-video recommendations, the collaborative filtering parameter values may be based on a video pair that includes a video in which a user has already demonstrated an interest. The machine learning engine generates a machine-learning score for each video. The machine learning scores are used as the basis for selecting which videos to recommend to a particular user.

Automatically recommending content

Growing community of inventors

Palo Alto, CA, United States of America

Nimrod Hoofien