Equifax Inc.

Stephen Leitner

Steven Hicklin

Mark Burgess

Keith Manthey

Lester Anthony Pieniazek

Keith W Manthey

Reuben S Kennedy

John M Dickson

Kevin W Manthey

Kevin M Franklin

Mark Nailor

Samuel Canfield

David A Ferber

Fred Hughes

Mark A Nailor

Frederick Hughes

Reuben Kennedy

Examples are disclosed for detecting synthetic online entities that may be used for fraudulent purposes or other purposes. In some aspects, a computing system can generate a data structure that includes nodes and links between the nodes. The nodes can represent online entities and the links can represent geographic associations or transactional associations between pairs of online entities. These associations can be identified from electronic transactions involving the online entities. The computing system can determine, from the links between the nodes, that a degree of connectivity among a subset of the nodes exceeds a threshold connectivity. The degree of connectivity indicates electronic communications involving online entities represented by the subset of the nodes. The computing system can transmit, based on the degree of connectivity exceeding the threshold connectivity, an alert indicating a potential synthetic entity (e.g., potentially fraudulent activity) within the subset of the nodes.

Detecting synthetic online entities

In some aspects, a computing system can receive a request for a processing operation that involves a query. The computing system can extract a query parameter indicating an entity or information type. The computing system can parse, using the query parameter, an obfuscated dataset that is generated by electronically transforming (i) first sensitive information into first obfuscated data using an obfuscation key and (ii) second sensitive information into second obfuscated data using the obfuscation key. The sensitive information is unreadable in the obfuscated data. The computing system can match the query parameter to the first obfuscated data and the second obfuscated data based on a relationship between the first obfuscated data and the second obfuscated data. The relationship is independent of a meaning of the first and second sensitive information. The computing system can performing the processing operation using the first and second obfuscated data.

Generating and processing obfuscated sensitive information

A global matching system can include a processing device and a memory device on which instructions can be stored. The processing device can execute the instructions to receive input data to be matched to target data stored in the memory device. The processing device can identify at least one context parameter for the input data. The context parameter indicate a location-specific characteristic or culturally specific characteristic of an entity associated with the input data. The processing device can access program code for matching tools and select a subset of the matching tools' program code based on the identified context parameter. The processing device can identify, based on the identified context parameter, an order of execution for the selected program code. The processing device can execute the selected program code in the identified order of execution and output a matching result for the input data and the target data.

Global matching system

Systems and methods are provided for conducting intelligent parallel searches of data sources. A search engine receives a request to access target data that is stored in at least one of multiple data sources. Each data source has a candidate index. The search engine extracts inquiry parameters from the request. The inquiry parameters corresponds to sub-indices of respective general indices. Each general index includes an index of relationships between data from at least two of the data sources. Each sub-index includes a subset of the respective general index. The search engine performs parallel searches of the general indices common to the data sources. Each parallel search includes searching the sub-indices based on corresponding inquiry parameters for the sub-indices. The search engine performs additional parallel searches of the candidate indices based on results of the parallel searches. The search engine extracts an output from results of the additional parallel searches.

Systems and methods for intelligent parallel searching

The present invention relates to methods and systems for automated criteria and attribute generation, searching, auditing and reporting of data. One aspect of an embodiment of the invention includes a method for translating a request for filtering data in a plurality of credit data sources. The method includes receiving a request based on at least one attribute and on at least one modeling criteria, wherein the at least one attribute and the at least one modeling criteria are each associated with a portion of data in a plurality of credit data sources, automatically generating executable computer code associated with the at least one attribute and at least one modeling criteria, wherein the executable computer code is adapted to filter the portion of data in the plurality of credit data sources based at least in part on the at least one attribute and at least one modeling criteria, and storing at least a portion of the executable computer code for use with another request based in part on the at least one attribute and based in part on the at least one modeling criteria.

Systems and processes for automated criteria and attribute generation, searching, auditing and reporting of data

Growing community of inventors

Alpharetta, GA, United States of America

Stephen Leitner