Verizon Business Global LLC

Verizon Patent and Licensing Inc.

Mci, Inc.

John Hans Van Arkel

Saralyn M Mahone

Arthur Lance Springer

Matthew J Gilbert

Thomas E Stepp

Terrill J Curtis

James J Wagner

Scott Hagins

David D Tada

Corrine L Schweyen

Jeffrey Allen Haltom

Lulia Ann Barakat

Charles Alan Dallas

Katrina Marie Kutchko

Mohammad Reza Tayebnejad

Karl Stang

Karl Aric Van Camp

Joe B Thornton

Visweswararao Ganti

Adam Young

Michael F Caslin

Michael Caslin

Disclosed are systems and methods for robocall steering over voice-hosted traffic networks. The disclosed framework provides novel systems and methods for increasing the accuracy and efficiency in tracking, identifying, blocking and preventing robocalls and robocallers. The disclosed systems and methods provide mechanisms for identifying and removing unwanted voice traffic from networks. The disclosed systems and methods analyze voice traffic over a predetermined period of time (e.g., 1 day or 30 days, for example), and leverage this information into a 'know your customer' (KYC) score. This score enables incoming calls to be routed, controlled and/or blocked as they are communicated over voice networks.

Computerized system and method for robocall steering

A device for using rules in the processing of information includes a first interface that allows for secure communications, a first database, a second database, a second interface that allows for secure communications, and a detection component implemented at least partially in hardware, the first interface connecting to the first database, the first database connecting to the detection component, the second database connecting to the detection component, the second interface connecting to the detection component, the second database including a plurality of rule libraries, each rule library, of the plurality of rule libraries, storing a set of related rules, and a plurality of rule engines, each rule engine, of the plurality of rule engines, corresponding to a rule library, of the plurality of libraries, and the detection component including a rule selector, and a rule applicator to apply a selected rule to information.

Predictive modeling processes for healthcare fraud detection

A device may identify information associated with other devices, generate a first value for one or more indicators associated with the information, process, based on providing the information to a rules engine corresponding to a library of rules including the rule and receiving, from the rules engine and based on providing the information to the rules engine, information associated with a second value the information using a rule to generate the second value based on combining the first value with one or more third values, and output information regarding the second value to determine how to process the information.

Near real-time detection of information

A system for providing secure communications may include a management system to receive first information, the first information being received via a first secure connection, analyze the received information to form analyzed information, and provide the analyzed information, a processor device to receive the analyzed information, the analyzed information being received via a second secure connection between the processor device and the management system, and perform an action based on the analyzed information, and a clearinghouse device to receive second information, the second information being received via a third secure connection between the clearinghouse device and each provider device of a plurality of provider devices, process the second information to form the first information, and provide the first information to the management system via the first secure connection.

Secure communications

A fraud management system is configured to store rules for detecting fraud. The fraud management system is further configured to receive a transaction involving a consumer and a merchant; obtain network security information associated with malicious activity in a voice network or a data network, where the network security information indicates that the consumer has been involved in malicious activity in the voice network or in the data network; select a subset of rules based on the network security information and information associated with the transaction, the merchant, or the consumer; process the transaction using the subset of rules to generate alarms; process the alarms to generate a fraud score for the transaction; and output information regarding the fraud score to the merchant to assist the merchant in determining whether to accept, deny, or fulfill the transaction.

Using network security information to detection transaction fraud

An approach provides detection of unauthorized use of data services. The number of data calls for access to a data network is tracked over a predetermined time period, and the cumulative duration of the data calls is determined. Thereafter, a determination is made as to whether the number of the data calls and the cumulative duration satisfy, respectively, a first threshold and a second threshold. A potential fraudulent use of the account is determined, if the thresholds are satisfied.

Method and apparatus for providing fraud detection using connection frequency and cumulative duration thresholds

An approach provides fraud detection in support of data communication services. A list of single-event attributes (e.g., hot or cold attributes) is generated and includes a network address of an end user host originating a data call or a calling party identification (e.g., Automatic Number Identification (ANI) or an originating Calling Line Identification (CLI)) for network access, wherein entries of the list specify values of the hot attributes. An attribute value associated with the data call is compared with the entries. A fraud alert is generated if the attribute value matches one of the entries.

Method and apparatus for providing fraud detection using hot or cold originating attributes

An approach provides detection of unauthorized use of data services. A determination is made as to whether connections supporting remote access to a data network are completed. The number of completed connections associated with a selected attribute is tracked over a time period. It is then determined whether the number of completed connections satisfies a connection frequency threshold. A fraud alert is generated if the connection frequency threshold is satisfied.

Method and apparatus for providing fraud detection using connection frequency thresholds

An approach provides fraud detection in support of data communication services. A usage pattern associated with a particular account for remote access to a data network is monitored. The usage pattern is compared with a reference pattern specified for the account. A fraud alert is selectively generated based on the comparison.

Method and system for providing fraud detection for remote access services

An approach provides fraud detection in support of data communication services. A threshold corresponding to a geographic location is set. The threshold corresponds to duration of a call supporting data communications. It is determined whether the call duration exceeds the threshold. A fraud alert is generated if the monitored call duration exceeds the threshold.

Method and apparatus for providing fraud detection using geographically differentiated connection duration thresholds

An approach provides detection of unauthorized use of data services. A fraud case is created for a data call that is determined to be potentially fraudulent based on a fraud alert. A fraud score is determined for the case according to the fraud alert. The fraud score is adjusted according to adjustment criteria including an intermediate network involved with the data call, and an originating country of the data call.

Method and system for prioritizing cases for fraud detection

A data processing system program to develop, train, and implement a neural network for identifying customers who represent a bad debt risk is disclosed. A feature vector is applied to a neural network to generate outputs that approximate the relative likelihood that customers who are the subjects of the records used to generate the feature vector will be a bad debt risk. Statistical values relating categorical attributes of the customers to the likelihood of their becoming a bad debt risk are substituted for the categorical attributes, and the attributes are normalized before the feature vector is applied to the network. In one embodiment the customers are customers of a long distance service provider.

Artificial intelligence trending system

A fraud monitoring system is disclosed for a communications system. The fraud monitoring system analyzes records of usage activity in the system and applies fraud pattern detection algorithms to detect patterns indicative of fraud. The fraud monitoring system advantageously accommodates transaction both records resulting from control of a packet-switched network and those from a circuit-switched network gateway.

Growing community of inventors

Colorado Springs, CO, United States of America

John Hans Van Arkel