Search Patents
  • Incremental model training for advertisement targeting using streaming data
    Patent number: 9384451
    Abstract: Incremental model training for advertisement targeting is performed using streaming data. A model for targeting advertisements of an advertising campaign is initialized. A data stream including data corresponding to converters and data corresponding to non-converters is received. The model is then applied to the data corresponding to the converter and data corresponding to the non-converter (or other ratio of converter to non-converters) to obtain a predicted score for each. The predicted score is compared to the observed score (e.g., an observed score of 1 for a converter, and 0 for a non-converter). The difference between the predicted and observed scores is computed, and the model is incrementally updated based on this difference. Models can optionally be built separately on multiple modeling servers that are geographically dispersed in order to support bidding on advertising opportunities in a real-time bidding environment.
    Type: Grant
    Filed: November 24, 2015
    Date of Patent: July 5, 2016
    Assignee: Quantcast Corporation
    Inventor: Gaurav Chandalia
  • Identifying variance in distributed systems
    Patent number: 10489383
    Abstract: Adaptive Sampling. Data comprising pairings of data value with lists of data keys are received. The range of possible values of the data keys is partitioned into unbalanced buckets, with at least two of the unbalanced buckets representing different fractions of the range. Each unbalanced bucket is assigned to a respective processing unit selected from a plurality of processing units. The pairings are processed by the processing units, with each processing unit generating an intermediate result. The intermediate results are combined to generate a comprehensive result. A sampling error is determined by scaling an unbalanced bucket's intermediate result according to its corresponding fraction and comparing the scaled intermediate result to the comprehensive result. An unbalanced bucket having a sampling error less than a sampling error threshold is selected. The selected unbalanced bucket's corresponding fraction is selected as a sampling rate for a second data processing job.
    Type: Grant
    Filed: June 30, 2017
    Date of Patent: November 26, 2019
    Assignee: Quantcast Corporation
    Inventor: Scott S. McCoy
  • Detecting and reporting on consumption rate changes
    Patent number: 8386601
    Abstract: A reporting system for providing reports on consumption rate changes for media content delivered over a network. A respective media consumption history is received for each of a plurality of entities at a storage. The histories are analyzed to identify selected media content for reporting based on changes in a consumption rate of the media content between at least two time intervals. A report including a reference to the selected media content is provided to a system. In an example, the system is a search engine indexing system and the invention enables the rapid indexing of new content and/or media content experiencing a surge in popularity. The consumption rate changes can be measured for monitored audiences comprising a subset of the audience. The monitored audience can be provided as a list of entities and/or selected based on the media consumption history and/or similarity to a known set of entities.
    Type: Grant
    Filed: July 2, 2010
    Date of Patent: February 26, 2013
    Assignee: Quantcast Corporation
    Inventors: Paul G. Sutter, Konrad S. Feldman
  • System and method for multibeaconing
    Patent number: 8090825
    Abstract: A method and system for triggering multiple client requests, including: providing directions for obtaining multibeacon instructions, in response to a content request from the client device, providing the multibeacon instructions in response to a request from the client device, with the request for multibeacon instructions submitted by the client device based on the directions, receiving an initial image request at the multibeacon management system from the client device wherein the initial image request is submitted by the client device upon execution of the multibeacon instructions, and, composing and sending a beacon from the multibeacon management system to the client device in response to the initial image request causing the configuration of a storage device at the client device for storing the beacon, wherein the properties of the beacon are configured to trigger the multibeacon instructions to instruct the client device to submit additional image requests to the multibeacon management system.
    Type: Grant
    Filed: April 19, 2010
    Date of Patent: January 3, 2012
    Assignee: Quantcast Corporation
    Inventor: Naveen Nalam
  • Using proxy behaviors for audience selection
    Patent number: 9183568
    Abstract: Method and system for assessing the suitability of an entity using a proxy. A description of a behavior associated with a desirable audience is received. A proxy behavior estimated to be characteristic of the desirable audience is selected. The proxy behavior comprises the performance of proxy events related to the consumption of media received by an entity over a network, which can be found in an entity's consumption history. An entity can be assessed for inclusion in a proxy audience, by examining the entity's consumption history for proxy behaviors. A behavioral model is built using a training set comprising the proxy audience. By applying the behavioral model to the consumption history of a specified entity, the specified entity's suitability for selection can be determined. Advantageously, in an embodiment, the invention enables the use of behavioral modeling techniques even when the complete behavior of the desirable audience is not available.
    Type: Grant
    Filed: March 31, 2014
    Date of Patent: November 10, 2015
    Assignee: Quantcast Corporation
    Inventors: Paul G. Sutter, Konrad S. Feldman
  • Protected audience selection
    Patent number: 11449897
    Abstract: Protected audience selection system. Media consumption histories of browsers which have converted are received at a modeling system where targeting of browsers is prohibity. A model is built by determining a frequency of each respective media consumption event among the histories and comparing each determined frequency of a respective media consumption event to a frequency of the respective media consumption event among a population of browsers without the conversion event. The model is sent to a targeting system which excludes conversion events. A description of the conversion event is received at the targeting system. A history of a targetable browser is received at the targeting system. The model is applied to the history of the targetable browser at the targeting system, where conversion events have been excluded from the history. Advertising content is sent to the targetable browser according to a result of applying the model.
    Type: Grant
    Filed: October 31, 2019
    Date of Patent: September 20, 2022
    Assignee: Quantcast Corporation
    Inventors: Konrad S. Feldman, Damian John Reeves, Paul G. Sutter
  • Automated persona feature selection
    Patent number: 11507604
    Abstract: Embodiments of the invention include a system for automated persona feature selection. Soft clusters of entities are received, each entity having a history of features. Each feature has a general prevalence coefficient representing prevalence of entities having the respective feature in their history. A feature list is generated for each cluster, each feature having an in-cluster coefficient representing prevalence of entities in the cluster having the feature in their history. Features having an in-cluster coefficient that is different from that feature's general prevalence coefficient are selected. A variance across the clusters is determined for each selected feature. A discriminating feature list having high variance features is generated for each cluster. Clusters are selected for an entity by comparing the features of the entity's history to features of the discriminating feature lists of the clusters. Content is customized according to the chosen clusters and sent to the entity.
    Type: Grant
    Filed: August 7, 2020
    Date of Patent: November 22, 2022
    Assignee: Quantcast Corporation
    Inventor: William Kennedy Browne
  • Automatic performance-triggered feature discovery
    Patent number: 10360581
    Abstract: Automatic performance triggered model adjustment. A hierarchical feature tree is generated. Each child node's feature is more specific than its respective parent node's feature. A behavioral model comprising features of the feature tree is created and used in the operation of an advertising campaign. A degraded model feature is detected at the discovery system by comparing a performance metric of a model feature from two different time windows. The discovery system matches a node of the feature tree with the degraded feature and selects a prospective model feature from a same-level node or from a lower level node than the matching feature's node. An estimated performance metric for the prospective model feature is determined and the results are used to decide if the model should be updated to include the prospective model feature. The campaign can be operated with the automatically updated model.
    Type: Grant
    Filed: October 22, 2014
    Date of Patent: July 23, 2019
    Assignee: Quantcast Corporation
    Inventor: Michael Recce
  • Protected audience selection
    Patent number: 11776010
    Abstract: Protected audience selection system. Media consumption histories of browsers which have converted are received at a modeling system where targeting of browsers is prohibited. A model is built by determining a frequency of each respective media consumption event among the histories and comparing each determined frequency of a respective media consumption event to a frequency of the respective media consumption event among a population of browsers without the conversion event. The model is sent to a targeting system which excludes conversion events. A description of the conversion event is received at the targeting system. A history of a targetable browser is received at the targeting system. The model is applied to the history of the targetable browser at the targeting system, where conversion events have been excluded from the history. Advertising content is sent to the targetable browser according to a result of applying the model.
    Type: Grant
    Filed: September 19, 2022
    Date of Patent: October 3, 2023
    Assignee: Quantcast Corporation
    Inventors: Konrad S. Feldman, Damian John Reeves, Paul G. Sutter
  • Automatic generation and management of advertising campaigns based on third-party listings
    Patent number: 9846895
    Abstract: Embodiments are directed to generating and managing an advertising campaign based on a third-party listing. In particular, an identifier associated with a listing posted over a third-party service from a user of the third-party service is received. Listing data for the listing is retrieved from the third-party service using the identifier associated with the listing. Thereafter, an advertising campaign is automatically generated based at least in part on the retrieved listing data. In one aspect, generation of the advertising campaign includes generating an advertising creative using the retrieved listing data. Subsequently, an advertising opportunity is selected according to the generated advertising campaign. Following the selection, an advertisement based on the advertising creative is provided to a content provider associated with the advertising opportunity.
    Type: Grant
    Filed: March 15, 2013
    Date of Patent: December 19, 2017
    Assignee: Quantcast Corporation
    Inventors: Silvius V. Rus, Barney Govan, Nhat Bao Sinh Vu, Mark Cooper
  • Identifying variance in distributed systems
    Patent number: 11182376
    Abstract: Adaptive Sampling. Data comprising pairings of data value with lists of data keys are received. The range of possible values of the data keys is partitioned into unbalanced buckets, with at least two of the unbalanced buckets representing different fractions of the range. Each unbalanced bucket is assigned to a respective processing unit selected from a plurality of processing units. The pairings are processed by the processing units, with each processing unit generating an intermediate result. The intermediate results are combined to generate a comprehensive result. A sampling error is determined by scaling an unbalanced bucket's intermediate result according to its corresponding fraction and comparing the scaled intermediate result to the comprehensive result. An unbalanced bucket having a sampling error less than a sampling error threshold is selected. The selected unbalanced bucket's corresponding fraction is selected as a sampling rate for a second data processing job.
    Type: Grant
    Filed: November 25, 2019
    Date of Patent: November 23, 2021
    Assignee: Quantcast Corporation
    Inventor: Scott S. McCoy
  • Protected audience selection
    Patent number: 10467655
    Abstract: Protected audience selection system. Media consumption histories of browsers which have converted are received at a modeling system where targeting of browsers has been disabled by excluding targeting labels. A model is built by determining a frequency of each respective media consumption event among the histories and comparing each determined frequency of a respective media consumption event to a frequency of the respective media consumption event among a population of browsers without the conversion event. The model is sent to a targeting system which excludes conversion events. A description of the conversion event is received at the targeting system. A history of a targetable browser is received at the targeting system. The model is applied to the history of the targetable browser at the targeting system in the absence of records of conversion events. Advertising content is sent to the targetable browser according to a result of applying the model.
    Type: Grant
    Filed: June 30, 2017
    Date of Patent: November 5, 2019
    Assignee: Quantcast Corporation
    Inventors: Konrad S. Feldman, Damian John Reeves, Paul G. Sutter
  • Balancing on-site engagement
    Patent number: 11494456
    Abstract: Encouraging broader engagement with a target publisher's content by balancing on-site topic engagement. Responsive to receiving notification of a recipient's request of an item of content from the target publisher, the on-site and off-site content consumption history of the recipient is analyzed. For each of a plurality of topics, historic engagement with on-site and off-site content is measured. Deficient topics having better off-site engagement than on-site engagement are detected. Content comprising links to items of content available from the target publisher which are characterized by deficient topics is selected and sent to the recipient. In an embodiment, the supplemental content comprises a plurality of links to other web pages on the target publisher's website which are sent to the recipient browser before the requested item of content finishes loading.
    Type: Grant
    Filed: August 31, 2020
    Date of Patent: November 8, 2022
    Assignee: Quantcast Corporation
    Inventors: Evyatar Ram, Akshay Patil, Chandra Cherukuri, Navin Viswanath, Sokratis Papafloratis, Vijay Kalyanaraman, Vikas Tawari
  • Automated persona feature selection
    Patent number: 10740359
    Abstract: Embodiments of the invention include a system for automated persona feature selection. Soft clusters of entities are received, each entity having a history of features. Each feature has a general prevalence coefficient representing prevalence of entities having the respective feature in their history. A feature list is generated for each cluster, each feature having an in-cluster coefficient representing prevalence of entities in the cluster having the feature in their history. Features having an in-cluster coefficient that is different from that feature's general prevalence coefficient are selected. A variance across the clusters is determined for each selected feature. A discriminating feature list having high variance features is generated for each cluster. Clusters are selected for an entity by comparing the features of the entity's history to features of the discriminating feature lists of the clusters. Content is customized according to the chosen clusters and sent to the entity.
    Type: Grant
    Filed: July 1, 2016
    Date of Patent: August 11, 2020
    Assignee: Quantcast Corporation
    Inventor: William Kennedy Browne
  • Managing distributed system performance using accelerated data retrieval operations
    Patent number: 10019316
    Abstract: A distributed system is adapted to manage the performance of distributed processes. In one aspect, multiple stripes associated with a data item are stored in a distributed storage. The stored stripes include one or more stripes of redundancy information for the data item. A distributed process including at least one task is performed. During performance of the distributed process, a determination is made as to whether to perform an accelerated data retrieval operation. Responsive to a determination to perform an accelerated data retrieval operation, at least one of the one or more stripes of redundancy information for the data item is requested from the distributed storage. Other stripes associated with the data item may also be requested from the distributed storage. After a sufficient subset of stripes associated with the data item is received, the data item is reconstructed using the subset.
    Type: Grant
    Filed: December 14, 2016
    Date of Patent: July 10, 2018
    Assignee: Quantcast Corporation
    Inventors: Esteban Molina-Estolano, Silvius V. Rus
  • Slow Network Detection and Response
    Publication number: 20220358536
    Abstract: A control system determines whether a browser is retrieving supplemental content over a slow or faulty network using a tracking indicator. Based on determining that browser is retrieving supplemental content over a slow or faulty network, the control system modifies responses to opportunities to provide supplemental content to the browser. The control system may modify responses by declining to bid, responding with a lower bid amount, or responding with alternate supplemental content. Based on determining that browser is no longer retrieving supplemental content over a slow or faulty network, the control system modifies responses to opportunities to provide supplemental content to the browser by responding with a higher bid amount or responding with the original supplemental content. Thus, the control system maximizes the use of control system and campaign manager resources by responding to opportunities according to the likelihood that they will result in an impression or a conversion.
    Type: Application
    Filed: July 25, 2022
    Publication date: November 10, 2022
    Applicant: Quantcast Corporation
    Inventor: Gurel Erceis
  • Automated load-balancing of partitions in arbitrarily imbalanced distributed mapreduce computations
    Patent number: 10642866
    Abstract: A distributed computing system executes a MapReduce job on streamed data that includes an arbitrary amount of imbalance with respect to the frequency distribution of the data keys in the dataset. A map task module maps the dataset to a coarse partitioning, and generates a list of the top K keys with the highest frequency among the dataset. A sort task module employs a plurality of sorters to read the coarse partitioning and sort the data into buckets by data key. The values for the top K most frequent keys are separated into single-key buckets. The other less frequently occurring keys are assigned to buckets that each have multiple keys assigned to it. Then, more than one worker is assigned to each single-key bucket. The output of the multiple workers assigned to each respective single-key bucket is stitched together.
    Type: Grant
    Filed: February 2, 2017
    Date of Patent: May 5, 2020
    Assignee: Quantcast Corporation
    Inventors: Wei Jiang, Silvius V. Rus
  • Managing distributed system performance using accelerated data retrieval operations
    Patent number: 9392060
    Abstract: A distributed system is adapted to manage the performance of distributed processes. In one aspect, multiple stripes associated with a data item are stored in a distributed storage. The stored stripes include one or more stripes of redundancy information for the data item. A distributed process including at least one task is performed. During performance of the distributed process, a determination is made as to whether to perform an accelerated data retrieval operation. Responsive to a determination to perform an accelerated data retrieval operation, at least one of the one or more stripes of redundancy information for the data item is requested from the distributed storage. Other stripes associated with the data item may also be requested from the distributed storage. After a sufficient subset of stripes associated with the data item is received, the data item is reconstructed using the subset.
    Type: Grant
    Filed: October 22, 2013
    Date of Patent: July 12, 2016
    Assignee: Quantcast Corporation
    Inventors: Silvius V. Rus, Esteban Molina-Estolano
  • Managing distributed system performance using accelerated data retrieval operations
    Patent number: 9612906
    Abstract: A distributed system is adapted to manage the performance of distributed processes. In one aspect, multiple stripes associated with a data item are stored in a distributed storage. The stored stripes include one or more stripes of redundancy information for the data item. A distributed process including at least one task is performed. During performance of the distributed process, a determination is made as to whether to perform an accelerated data retrieval operation. Responsive to a determination to perform an accelerated data retrieval operation, at least one of the one or more stripes of redundancy information for the data item is requested from the distributed storage. Other stripes associated with the data item may also be requested from the distributed storage. After a sufficient subset of stripes associated with the data item is received, the data item is reconstructed using the subset.
    Type: Grant
    Filed: May 24, 2016
    Date of Patent: April 4, 2017
    Assignee: Quantcast Corporation
    Inventors: Esteban Molina-Estolano, Silvius V. Rus
  • Automated load-balancing of partitions in arbitrarily imbalanced distributed mapreduce computations
    Patent number: 9613127
    Abstract: A distributed computing system executes a MapReduce job on streamed data that includes an arbitrary amount of imbalance with respect to the frequency distribution of the data keys in the dataset. A map task module maps the dataset to a coarse partitioning, and generates a list of the top K keys with the highest frequency among the dataset. A sort task module employs a plurality of sorters to read the coarse partitioning and sort the data into buckets by data key. The values for the top K most frequent keys are separated into single-key buckets. The other less frequently occurring keys are assigned to buckets that each have multiple keys assigned to it. Then, more than one worker is assigned to each single-key bucket. The output of the multiple workers assigned to each respective single-key bucket is stitched together.
    Type: Grant
    Filed: June 30, 2014
    Date of Patent: April 4, 2017
    Assignee: Quantcast Corporation
    Inventors: Silvius V. Rus, Wei Jiang
Narrow Results

Filter by US Classification