Fair Isaac Corporation

Burning Glass Technologies, LLC

Hnc Software, Inc.

Visa International Service Association

Anu Kumar Pathria

Jean De Traversay

Michael K Tyler

Nallan C Suresh

Louis S Biafore

Krassimir G Ianakiev

William M Ferguson

Arati S Deo

Hyma Gollamudi

Michael A Lazarus

Dayne B Freitag

Theodore James Crooks

Ho Ming Luk

Craig Nies

Mark Alan Laffoon

Allen Jost

Matthew N Dailey

Andrea L Allmon

Krishna M Gopinathan

Edmond D Chow

Mary Reeder

Krishna Gopinathan

Sean M Downs

Benjamin A Friesen

Chalaporn Hathaidharm

Steven A Wickert

Pamela E Coates

Systems and methods for verifying a distant-from-home financial transaction related to a customer account based on travel indicators in earlier purchase transactions made by that customer.

System and method for financial transaction authentication using travel information

Fraud and abuse detection in an entity's payment coding practices includes the ability to search for fraud at all levels of the hierarchical coded payment system within the context of an unsupervised model. The model uses variables derived and profiles created at any level or at all levels of the hierarchical coded payment system to create a comprehensive description of the payment coding activities submitted by the entity. That description is compared with other peer entities to determine unusual and potentially inappropriate activity. The profiles created may themselves be utilized for purposes other than the detection of fraud and abuse.

Detection of upcoding and code gaming fraud and abuse in prospective payment healthcare systems

Transaction-based behavioral profiling, whereby the entity to be profiled is represented by a stream of transactions, is required in a variety of data mining and predictive modeling applications. An approach is described for assessing inconsistency in the activity of an entity, as a way of detecting fraud and abuse, using service-code information available on each transaction. Inconsistency is based on the concept that certain service-codes naturally co-occur more than do others. An assessment is made of activity consistency looking at the overall activity of an individual entity, as well as looking at the interaction of entities. Several approaches for measuring consistency are provided, including one inspired by latent semantic analysis as used in text analysis. While the description is in the context of fraud detection in healthcare, the techniques are relevant to application in other industries and for purposes other than fraud detection.

Consistency modeling of healthcare claims to detect fraud and abuse

Detection of insurance premium fraud is provided by a predictive model, which uses derived variables to assess the likelihood of fraud for each policy. The predictive model produces a score, which is a measure of the likelihood of premium fraud or abuse. The predictive model is included in a system that accepts policies to be considered for scoring, selects which policies are appropriate for scoring, stores data about the policies in a database, uses the data to derive variables for the model, and processes and outputs the model scores and related information. A rule-based analysis, which detects specific inconsistencies in the data that are indicative of premium fraud, may also be part of the system. The model scores and red-flag indicators from the rule-based analysis may be further processed to provide customized output for users.

Detection of insurance premium fraud or abuse using a predictive software system

Transition probability sequencing models and metrics are derived from healthcare claims data to identify potentially fraudulent or abusive practices, providers, doctors, clients, or other entities. Healthcare reimbursement claims from hospitals, skilled nursing facilities, doctors, etc., are processed to identify sequences of states, and transition probability metrics are determined from frequency information pertaining to the states. The metrics can these be further analyzed in predictive or rule based models, or other tools.

Sequencing models of healthcare related states

A system, computer program product, and method provide for reason driven data analysis in a web-based system that is configurable to various types of data and environments. The computer program product provides for navigation of a report tree of reports that are hierarchically organized with respect to reasons derived from an analysis of transactional data in a database. A frame based interface provides for easy and flexible navigation and configuration of the reports and other features. A configuration file is used to rapidly develop and customize the web-based system. Case management functionality is included to allow for management of cases being reviewed using the system.

Webstation: configurable web-based workstation for reason driven data analysis

Computer implemented processes and software products generate profiles of entities, such as providers, clients, merchants and customers, and entities comprising interacting pairs of entities. The processes including deriving direct profiles from transaction data pertaining to an entity and enhancing the profile of one entity using the profile of another entity. Parallel and serial applications of the derive and enhance processes on various individual and multiple entites yields enhanced profiles that powerfully describe the interactions and relationship of the entities to each other, and between their members.

Cascaded profiles for multiple interacting entities

A Hidden Markov model is used to segment a data sequence. To reduce the potential for error that may result from the Markov assumption, the Viterbi dynamic programming algorithm is modified to apply a multiplicative factor if a particular set of states is re-entered. As a result, structural domain knowledge is incorporated into the algorithm by expanding the state space in the dynamic programming recurrence. In a specific example of segmenting resumes, the factor is used to reward or penalize (even require or prohibit) a segmentation of the resume that results in the re-entry into a section such as Experience or Contact Information. The method may be used to impose global constraints in the processing of an input sequence or to impose constraints to local sub-sequences.

Method for improving results in an HMM-based segmentation system by incorporating external knowledge

The similarity between two data objects of the same type (e.g., two resumes, two job descriptions, etc.) is determined using predictive modeling. A basic assumption is that training datasets are available containing compatibility measures between objects of the first type and data objects of a second type, but that training datasets measuring similarity between objects of the first type are not. A first predictive model is trained to assess compatibility between data objects of a first type and data objects of a second type. Then, in one scenario, pairs of objects of the first type are compared for similarity by running them through the first predictive model as if one object of the pair is an object of the first type and the other object of the pair is an object of the second type. Alternatively, for each object in a set of objects of the first type, the first predictive model is used to create a respective vector of compatibility scores against a fixed set of objects of the second type; these various vectors are then used to derive measures of similarity between pairs of objects of the first type, from which a second predictive model is trained, and the second predictive model is then used to assess the similarity of pairs of objects of the first type.

Application-specific method and apparatus for assessing similarity between two data objects

A method and apparatus is disclosed for making predictions about entities represented in documents and for information analysis of text documents or the like, from a large number of such documents. Predictive models are executed responsive to variables derived from canonical documents to determine documents containing desired attributes or characteristics. The canonical documents are derived from standardized documents, which, in turn, are derived from original documents.

Method and apparatus for making predictions about entities represented in documents

An automated system and method detects fraudulent transactions using a predictive model such as a neural network to evaluate individual customer accounts and identify potentially fraudulent transactions based on learned relationships among known variables. The system may also output reason codes indicating relative contributions of various variables to a particular result. The system periodically monitors its performance and redevelops the model when performance drops below a predetermined level.

Growing community of inventors

La Jolla, CA, United States of America

Anu Kumar Pathria