Google Inc.

James Hyunsoo Koh

Linus Page Chou

Jacob Burton Matthews

Paul J Baker

Maciej Babinski

Jige Yu

Jonathan Klem

James Edward Stewart

Eric W Ewald

Paul Sliwowski

Andrey Petrov

Carolyn R Marshall

A system for user association attribution may include one or more processors and memory. The one or more processors may receive information pertaining to relationship events that each correspond to a participant and one of several entities in a social network, allocate, for each relationship event, attribution values to touchpoints accessed by the corresponding entity prior to the relationship event. The processors may further determine a weight for each of the attribution values allocated to each of the touchpoints, where the weight for each of the attribution values is based at least in part on each of the relationship events for which each of the attribution values was allocated, generate an aggregate attribution value for each of the touchpoints based at least in part on the weighted attribution values allocated to each of the touchpoints, and provide, to the participant, each aggregate attribution value generated for each of the touchpoints.

User association attribution system

A system and machine-implemented method for providing effectiveness indications for social networking activity including receiving a request to provide an effectiveness score, identifying a plurality of actions performed with respect to the social networking activity by one or more other users exposed to the social networking activity, determining the total number of unique users performing the action, calculating an activity score for the social networking activity based on the determined number of users, determining a number of the users exposed to the social networking activity, calculating an effectiveness score for the social networking activity based on the total activity score and the number of users exposed to the social networking activity, wherein the effectiveness score comprises calculating the effectiveness score at least in part based on a ratio of the activity score to the number of the users exposed to the to the social networking activity.

Measuring effectiveness of social networking activity

A system for metric obfuscation may include one or more processors and memory. The one or more processors may receive a dataset comprising a plurality of metrics that relate to user demographic information and may generate a seed based at least in part on the dataset. The one or more processors may initialize a pseudorandom number generator with the seed and may generate a plurality of pseudorandom numbers using the pseudo-random number generator. The one or more processors may generate a plurality of obfuscated metrics corresponding to the plurality of metrics, wherein each of the plurality of obfuscated metrics is generated at least in part based on a corresponding metric of the plurality of metrics and a corresponding pseudorandom number of the plurality of pseudorandom numbers. The one or more processors may provide the plurality of obfuscated metrics.

Metric obfuscation system

Growing community of inventors

Chicago, IL, United States of America

James Hyunsoo Koh