Comscore, Inc.

Frank Pecjak

Ramzi Joseph Nasr

Brian Pugh

Magid M Abraham

Ying Li

Cameron Meierhoefer

Balakrishnan Vinayak Nair

Kris Johnson

Christopher Shea Haarstick

Michael J Vinson

John Clougherty

Josh Chasin

Bonnie E Harvey

Xuyao Jiang

Pakawat Phalitnonkiat

Douglas J Honnold

Joseph Lahr

Jonathon C Peruski

Online consumption data may be secured by receiving data associated with first online interactions actually performed during a predetermined time period, generating, via a machine learning model for each of a plurality of different personas, data associated with second online interactions that simulate Internet traffic, selecting a plurality of the received data associated with the first online interactions that matches the generated data associated with the second online interactions of one or more of the personas, replacing the generated data associated with the second online interactions of the one or more personas with the selected data, and outputting the one or more personas with the replaced data.

Generating behavioral profiles

Techniques for projecting household-level viewing events are described herein. Population data may be accessed including classes of a plurality of demographic attributes for households in a market. Representative household units (RHUs) may be generated, and the RHUs may be assigned a class for each of the demographic attributes and a quota based on the demographic attributes of a plurality of panelist households. Each of the panelist households may be assigned to one of the RHUs based on at least one panelist classes matching the classes for respective demographic attributes of the RHU, and the number of matching panelist households assigned to each of the RHU may be based on the quota. Panelist viewing data representing viewing events associated with the panelist household may be accessed. A report may be generated with the classes of the RHUs and the panelist viewing data of the assigned panelist households.

Deterministic household assignment model

Mobile usage data representing the access of one or more resources on a network by mobile devices is accessed. The mobile usage data includes information received from mobile devices as a result of beacon instructions included with the one or more resources. A first set of data representing information about accesses to the one or more resources by mobile devices with persistent beacon cookies is determined. A second set of data representing information about accesses to the one or more resources by mobile devices with non-persistent beacon cookies is determined. One or more adjustment factors are determined based on the first set of data. A count of unique visitors accessing the one or more resources from the mobile devices is determined based on a count of accesses by the mobile devices with persistent beacon cookies and a count of accesses by the mobile devices with non-persistent beacon cookies adjusted by the one or more adjustment factors.

Combining measurements based on beacon data

Measuring a networked audience is described. Initially, a first set of network usage data based on access of a resource by a first set of client systems is received. Next, a second set of network usage data based on access of the resource by a second set of client systems using a monitoring application installed on the second set of client systems is determined. Usage of the resource based on the first set of network usage data during a time period and one or more adjustment factors based on the second set of network usage data are determined. The determined usage is adjusted using the one or more adjustment factors. Finally, one or more audience reports for the resource using the adjusted usage are generated.

Measurements based on panel and census data

Aggregating viewership data is disclosed. Initially, household viewership data assigned to a tuning event in multiple households is accessed. Then, the household viewership data for the tuning event in the multiple households representing the same episode is aggregated to generate episode viewership data. Next, episode viewership data representing multiple episodes of the same program is aggregated to generate program viewership data. Next, the program viewership data for multiple programs of the same network is aggregated to generate network viewership data. Finally, the network viewership data for multiple commonly-owned networks is aggregated to generate entity viewership data.

Demographic attribution of household viewing events

Techniques for projecting person-level viewership from household-level tuning events are described. Initially, panelist viewing data are accessed and a plurality of state values based on the panelist viewing data are determined. Then, tuning data representing tuning events associated with particular households are accessed. For at least one tuning event represented by the tuning data, household member data is accessed, a portion of the panelist viewing data whose panelist information matches at least a portion of the member data is determined, a total number of watched minutes of the program by an individual member and a number of continuous series of watched states of the program by the individual member is determined, and an output representative of a probability that the particular portion of the program was watched by one or more of the individual members is generated.

Person level viewership probabilistic assignment model with Markov Chain

Measuring a networked audience is described. Initially, a first set of network usage data is determined based on a first set of signaling information obtained from a first subset of the client systems as a result of the first subset accessing common resources. In addition, a second set of network usage data is determined based on a second set of information obtained from a second subset of the client systems as a result of an application installed thereon monitoring accessing of the common resources. Usage is measured based on the first set of network usage data by determining an initial count of unique visitors that accessed the common resources by determining a count related to signaling of the first set of signaling information. Adjustment factors are determined based on the second set of network usage data. Finally, audience reports are generated by adjusting the measured usage using the one or more adjustment factors.

Usage data representing the access of a network entity by a plurality of client devices each associated with one or more Internet Protocol (IP) addresses of a plurality of IP addresses is initially accessed. Then a set of static IP addresses of the plurality of IP addresses is determined based on the usage data. A first count of static IP addresses of the set of static IP addresses that are all associated with mobile traffic or that are all associated with non-mobile traffic is determined. A second count of static IP addresses of the set of static IP addresses that are associated with the mobile traffic and the non-mobile traffic is also determined. An overlap factor is determined based on a ratio between the first count of static IP addresses and the second count of static IP addresses. Based on the overlap factor, a total count of unique static IP addresses via which the network entity was accessed is finally determined.

Tuning data representing a television viewing event associated with a particular household is accessed. Household member data representing information on individual members of the particular household is accessed. Viewing profile data representing information on individual members of other households regarding viewership by the individual members of the other households is accessed. Fractional viewership values for the individual members of the particular household are determined based on the tuning data, the household member data, and the viewing profile data. Household viewership data is determined based on the fractional viewership values.

A first set of usage data for a first set of resources on a network and a second set of usage data for a second set of resources on a network are accessed. The first set of resources were accessed by a first group of client systems and the first set of usage data is determined based on information received from the first group of client systems sent as a result of beacon instructions included with the first set of resources. The second set of usage data is determined based on information received from monitoring applications installed on a second group of client systems that accessed the second set of resources. Users of the second group of client systems are a sample of a larger group of users that use resources on the network. Initial usage measurement data for a third set of resources on the network is determined based on the first set of usage data. The third set includes one or more common resources that are included in the first set of resources and the second set of resources. One or more adjustment factors are determined based on the second set of usage data and applied to the initial usage measurement data to generate adjusted usage measurement data. One or more reports are generated based on the adjusted usage measurement data.

Usage data representing the access of a set of resources on a network is accessed. The usage data is based at least in part on information received from client systems sent as a result of beacon instructions included with the set of resources. First and second sets of usage data representing access by client systems classified as a first type and a second type, respectively, are determined based on the accessed usage data. Counts of unique visitors accessing the network resources from each of the first and second types of client systems, based on the first and sets of usage data, respectively, are each determined. A total count of unique visitors accessing the network resources from the first and second types of client systems is determined based on data representing the usage overlap of devices of the first type with devices of the second type.

In general, systems, components, methods, and techniques for gathering, recording, and development of accurate user demographics attributed to accesses by client systems of webpage, web content, or other online resources is provided. For a given a subset of unique users having known demographics for a segment of traffic or general population, a demographic profile may be created for all users of the segment or population within a tolerable margin of error. Demographic data for unique machine identifications (IDs) may be assigned, aggregated, and derived from a single source, or multiple sources, such as panel data, beacon level surveys, cookie exchanges, and the overlay of profile cookies from other publishers.

Attribution of demographics to census data

The present disclosure describes techniques for projecting person-level viewership from household-level tuning events. One example method includes accessing tuning data representing television tuning events associated with particular households; accessing panelist viewing data representing television viewing events associated with panelists; and for at least one tuning event represented by the tuning data: accessing household member data associated with the tuning event; determining a member minutes value associated with each individual member of the particular household for the tuning event; and determining a fractional viewership value for each individual member of the particular household associated with the tuning event.

Growing community of inventors

Fairfax Station, VA, United States of America

Frank Pecjak