Dstillery, Inc.

Rodney Alan Hook

Ori M Stitelman

Brian Dalessandro

Melinda Han Williams

Andrew Pancer

Blake Aber

Tommy Yiwel Mei

Claudia Reisz

Yuva Manhendran

Claudia Riesz

A system and method for analyzing media requests and evaluating the authenticity of geographic data associated with the media requests. A mobile device may use media requests to retrieve media items that are displayed to a user. A media request may include geographic data with latitude and longitude information and entity data identifying a user, application, mobile device, or combination thereof. The system may analyze the geographic data to identify locations and may analyze the entity information to identify user activity. The user activity may be internet activity of an application running on another device (e.g., user's desktop). The system may then correlate the user activity (e.g., accessing a venue web site) with the geographic locations (e.g., venue locations) to evaluate the authenticity of the geographic data associated with the mobile requests.

Evaluating the authenticity of geographic data based on user activity correlations

Evaluating the authenticity of geographic data based on spatial distribution

Some embodiments described herein relate to a method that includes surveying and/or passively monitoring content consumption by mobile communication devices. Each signal received from a mobile communication device can be associated with a common location. For example, an out-of-home device positioned at the location can be operable to receive requests from mobile communication devices that represent requests to access network locations. An audience profile for that common location can be defined based on a network location that is identified as being statistically overrepresented. Content targeted to the audience profile at the common location can then be provided.

Methods and apparatus for defining an audience for a particular location by surveying nearby receivers and/or passively monitoring content consumption

Evaluating authenticity of geographic data associated with media requests

A non-transitory processor-readable medium is provided that stores code representing instructions to be executed by a processor to receive data associated with access by a first plurality of entities to a first website location and to receive data associated with access by a second plurality of entities to a second website location. The processor is also caused to define a co-visitation factor for each of the first website location and the second website location based on the received data. The processor is also caused to, if the co-visitation factor of the first website location and/or the co-visitation factor of the second website location is over a predefined threshold, select the first website location and/or the second website location as target website locations. The processor is caused to send a signal to set a flag associated with each target website location indicating the target website location as a suspicious website location.

Methods, systems and media for detecting non-intended traffic using co-visitation information

A non-transitory processor-readable medium is provided that stores code representing instructions to be executed by a processor to filter data associated with an entity for a first predefined time period in response to an access by the entity at a first time to a preselected network location from a plurality of preselected network locations. The plurality of preselected network locations are associated with forced web traffic patterns. The processor is also caused to filter data associated with the entity for a second predefined time period in response to an access by the entity at a second time to a preselected network location from the plurality of preselected network locations during the first predefined time period. The second time is after the first time.

Methods and apparatus for detecting and filtering forced traffic data from network data

A complete end-to-end modeling system is provided that includes data sampling, feature engineering, action labeling, and model learning or learning from models built based on collected data. The end-to-end modeling process is performed via an automatic mechanism with minimal or reduced human intervention. A processor-readable medium is disclosed, storing processor-executable instructions to instantiate an automated data sampling and prediction structure training component, the automated data sampling and prediction structure training component being configured to automatically collect user event data samples, and use the collected user event data samples to train multiple prediction structures in parallel.

Methods and system for providing simultaneous multi-task ensemble learning

A non-transitory processor-readable medium stores code representing instructions to be executed by a processor to receive data associated with access by a first plurality of entities to a first website location and to receive data associated with access by a second plurality of entities to a second website location. The processor is also caused to define a co-visitation factor for each of the first website location and the second website location based on the received data. The processor is also caused to, if the co-visitation factor of the first website location and/or the co-visitation factor of the second website location is over a predefined threshold, select the first website location and/or the second website location as target website locations. The processor is caused to send a signal to set a flag associated with each target website location indicating the target website location as a suspicious website location.

Growing community of inventors

New York, NY, United States of America

Rodney Alan Hook