Comcast Cable Communications, LLC

Freewheel Media, Inc.

Visible World, Inc.

Robert Alan Bress

Seth M Haberman

Claudio Marcus

Zhao Xing

Christopher Paul Whitely

Gerrit Niemeijer

Tracy Nguyen

James Southern

Andrew Pagtakhan

Methods, systems, and apparatuses for audience metric determination are described herein. An audience segment may be targeted for delivery of content. A clustering algorithm may be used to categorize a quantity of users or devices into subsets based on a propensity to consume, present or output a particular type of content, and a quantity of time to output the particular type of content. A weight may be assigned to each subset based on its relevance to other subsets, such as based on data variance, e.g., on a distance to a midpoint of a specific subset of the subsets. An index parameter may be determined for the datasets, e.g., based on each weight for each subset, and data may be generated that reflects a ranking of content delivery spots for delivery of content to the audience segment.

Systems, methods, and apparatuses for audience metric determination

A content provider may receive an indication for supplemental content to be output to a target audience, determine a first content item to be viewed by the target audience based on one or more characteristics of the target audience, and may send an indication for the supplemental content to be output at a time associated with the output of the first content item. The content provider may determine a quantity of devices which output the supplemental content for a first time and may determine that this quantity of devices is below a target quantity of devices to output the supplemental content for the first time during a particular time period. The content provider may determine a second content item to be viewed by the target audience and may send an indication for the supplemental content to be output at a time associated with output of the second content item.

Device analysis for supplemental content exposure

Methods and systems for content optimization are described. A computing device may determine a predictability score that indicates a probability that a device will access a first content item. The computing device may send a second content item associated with the first content item. The second content item may be based on the predictability score, and the predictability score may be modified. Additional content consumption and/or recommendations may be adjusted based on the predictability score.

Methods and systems for predicting content consumption

Systems, methods and computer-readable media for a decentralized application system that enables participating parties to automate the buying and selling of TV media units and/or aggregated TV and premium video audiences is described. The value-based TV/premium video media exchange application system allows the participants to interact with the system directly and/or automate transactions and execution between systems, while ensuring proper governance over each participants own rules and economics associated with the transactions, as well as individual campaign constraints and requirements. The decentralized application system significantly lowers current transaction and execution barriers, timing and costs, while providing a highly accountable and trusted system across all of the exchange participants.

Value-based TV advertising audience exchange

Systems and methods for the optimized allocation of content on a content distribution system according to a content distribution plan are described. In some embodiments, a management system may be configured to generate an optimized schedule for content distribution, such as an advertising campaign. For a television distribution schedule, an impressions forecast may be generated based on the available inventory and historical audience measurement information, such as television ratings for a television advertising campaign. An optimized schedule may be generated based on the impressions forecast and content may be distributed according to the optimized schedule. Measurement information relating to the distribution according to the optimized schedule may be analyzed and used to generate a re-optimized schedule, for example, that may be used to schedule the advertising campaign on a subsequent day.

Methods, systems, and computer-readable media for dynamic content allocation

Systems and methods for the optimized allocation of content within a universe of inventory are described. For example, a method may include receiving content comprising at least one characteristic and at least one goal. A universe of inventory may be accessed that comprises a plurality of targets which may be assigned into a plurality of segments based on at least one demographic vector. An allocation optimization model may be generated based on the at least one content characteristic, the at least one goal and the plurality of segments. The content may be presented to the targets based on the allocation optimization model. Viewing data may be received that comprises data associated with target consumption of the content and the allocation optimization module may be re-optimized based on the viewing data. Additional factors, such as resource constraints and/or filtering rules, may be used when re-optimizing the allocation optimization module.

Dynamic content allocation and optimization

Methods, systems, and apparatuses for determining viewership of a content item are described herein. Machine learning techniques may be used to determine which user(s) among a user group at a multi-user location is consuming a content item. A machine learning model may be trained using demographic attributes and content attributes associated with a plurality of single-user locations. A probability engine may train a machine learning model using the demographic attributes and content attributes and one or more machine learning algorithms. The trained machine learning model may be used to determine which user(s) among at least two users is consuming a content item at a multi-user location at which multiple people reside.

Growing community of inventors

New Providence, NJ, United States of America

Robert Alan Bress