Abstract: An identity graph is partitioned into records pertaining to entities with similar data. A single authentication string or asserted relationship (AR) that represents a person identifies the person in the graph whose composite information is closest to the input by using all of the available context provided by the input string. By providing more contextual data to the match service than simply a name and single touchpoint, the service is able to match to a more focused and unique set of persons. In certain embodiments, the invention allows for the ability to take a small set of input data and more accurately identify its location in an identity graph much faster in time and lower in computational cost.

Abstract: An environment measures the value of data sources as input to an identity graph in terms of the impact of the inclusion or removal of the data sources. Combinations of candidate sources are delivered to a sandbox environment to generate the desired output. A person process, a person plus touchpoint process, and an activity value process are executed. Results include whether a person was added or removed; whether a person created a point of failure; and whether persons were consolidated or a person was split. The output provides an analysis of the evolution of an identity graph within an entity resolution system based on the choice of data sets used to build the graph.

Abstract: A machine analyzes an entity resolution data graph using a curated peer review set of data structures. The machine uses independent peer data structures that model similar or related yet different universes and entities. These data structures may include other entity resolution data graphs or file-based data structures. The machine first performs candidate screening to determine which of these data structures meet the requirements for use in the analysis. The machine then selects from among the candidate peer data structures with which to perform the analysis. Finally, the entity resolution data graph is analyzed using queries against the selected peer data structures to provide an analysis of the quality of its data graph.

Abstract: A system and method for the creation of household links (HHLs) associates each household with particular consumers associated with a consumer link (CL) and an address link (AL). The system and method utilize a feedback loop system to maintain persistence of HHLs over time and more accurately resolve HHLs. Top-down and bottom-up clustering methods are applied to the data, and the best results are taken to generate the final association of HHLs with particular ALs and CLs. By more accurately identifying the households associated with particular consumer data, the invention significantly reduces the storage requirements and time required for processing very large consumer data sets.

Abstract: A distributed node cluster architecture within a parallel computing environment provides for the association of individuals and households accessing a communications network through multiple electronic communications devices with a particular digital touchpoint or touchpoints used when communicating on the network. The cluster facilitates the determination of a touchpoint when an individual or household name is determined, or, alternatively, the determination of an individual or household when a touchpoint is received. A persistent linkage of digital touchpoints to individuals or households communicates with an entity resolution system executing at the node cluster to track data pertaining to entities, allowing the coordination of touchpoints with such individual consumers or households over time.

Abstract: An entirely automated system for the interpretation of the field layout for multi-field files uses a rich contextual framework constructed by the interaction of three subsystems to provide a holistic view of the contexts of a structured data file as defined by the location and data type of each field. The roles of each of the subsystems are (1) the determination of the file's metadata and positions of the different data fields; (2) the use of fallible oracles (i.e., no oracle must be capable of identifying the type for every record) to provide a set of interpretations of the fields at several levels; and (3) the accurate determination of the location and specific data type for each field without the necessity to interpret every record correctly, even in the presence of ambiguity of data. The system may operate on both delimited and fixed-width structure files.

Abstract: A system and method for the creation of household links (HHLs) associates each household with particular consumers associated with a consumer link (CL) and an address link (AL). The system and method utilize a feedback loop system to maintain persistence of HHLs over time and more accurately resolve HHLs. Top-down and bottom-up clustering methods are applied to the data, and the best results are taken to generate the final association of HHLs with particular ALs and CLs. By more accurately identifying the households associated with particular consumer data, the invention significantly reduces the storage requirements and time required for processing very large consumer data sets.

Abstract: A system and method for the creation of household links (HHLs) associates each household with particular consumers associated with a consumer link (CL) and an address link (AL) in order to more accurately identify consumers who are part of the same household. The system and method utilizes a feedback loop system to maintain persistence of HHLs over time and more accurately resolve HHLs from information ingested from multiple files containing consumer information. Both point-in-time (PIT) and temporal data are used. Top-down and bottom-up clustering methods are applied to the data, and the best results are taken to generate the final association of HHLs with particular ALs and CLs. By more accurately identifying the households associated with particular consumer data, the invention significantly reduces the storage requirements and time required for processing very large consumer data sets, allowing, for example, processing of such data on standard desktop computers.

Abstract: A method and apparatus for name variant extraction from individual handle identifiers uses a sequential extraction process to construct contextual information. Last name data, first/middle name data, initials, nicknames, and vanity names, along with numerical information indicating dates, may all be captured in extracting information about an individual associated with a particular handle. When multiple possible interpretations result from the analysis, those interpretations are ranked using optimality rules. The resulting data may be used to look up additional information in a consumer database in order to structure a targeted marketing message to the individual associated with the handle.

Abstract: An entirely automated system for the interpretation of the field layout for multi-field files uses a rich contextual framework constructed by the interaction of three subsystems to provide a holistic view of the contexts of a structured data file as defined by the location and data type of each field. The roles of each of the subsystems are (1) the determination of the file's metadata and positions of the different data fields; (2) the use of fallible oracles (i.e., no oracle must be capable of identifying the type for every record) to provide a set of interpretations of the fields at several levels; and (3) the accurate determination of the location and specific data type for each field without the necessity to interpret every record correctly, even in the presence of ambiguity of data. The system may operate on both delimited and fixed—width structure files.

Abstract: A system and method for the creation of household links (HHLs) associates each household with particular consumers associated with a consumer link (CL) and an address link (AL) in order to more accurately identify consumers who are part of the same household. The system and method utilizes a feedback loop system to maintain persistence of HHLs over time and more accurately resolve HHLs from information ingested from multiple files containing consumer information. Both point-in-time (PIT) and temporal data are used. Top-down and bottom-up clustering methods are applied to the data, and the best results are taken to generate the final association of HHLs with particular ALs and CLs. By more accurately identifying the households associated with particular consumer data, the invention significantly reduces the storage requirements and time required for processing very large consumer data sets, allowing, for example, processing of such data on standard desktop computers.

Abstract: A method and apparatus for name variant extraction from individual handle identifiers uses a sequential extraction process to construct contextual information. Last name data, first/middle name data, initials, nicknames, and vanity names, along with numerical information indicating dates, may all be captured in extracting information about an individual associated with a particular handle. When multiple possible interpretations result from the analysis, those interpretations are ranked using optimality rules. The resulting data may be used to look up additional information in a consumer database in order to structure a targeted marketing message to the individual associated with the handle.