By John L. Guerra
Editor, GRC & Fraud Software Journal
A new method for halting fraudulent phone calls before the victim takes the bait; a new way to catch online fraud by monitoring texts, emails and other digital communication; and other fraud prevention and detection patents are among the ideas recently filed at the U.S. Patent and Trademark Office.
Here's a look at recent fraud, risk, and compliance software patent filings. The wording of each company's abstract is exactly as it appears in the patent. Click on each title to see the full patent.
Date filed: April 6, 2017
Applicant: MasterCard International Incorporated
A method is disclosed for performance by at least one server, for securing an electronic transaction request from a computing device for fraud detection.
The request is received as a data packet comprising at least identification data of a payment card associated with the transaction and a MAC address of the computing device, is disclosed.
The method comprises the server comparing the MAC address with at least a first list of MAC addresses to obtain a first determination; the server using the identification data to obtain at least one second determination; and the server transmitting a response to the computing device to accept or decline the request based on the first determination and the at least one second determination.
A related computing device and server are also disclosed.
Date filed: Oct. 6, 2016
Applicants: Sik Piu Kwan, Jun Li
Various embodiments herein each include at least one of systems, methods, software, and devices, such as product scanners e.g., barcode scanners) enabled to detect item substitution fraud during a checkout process at facilities, such as retail outlets.
One method embodiment that may be performed in part on a product scanner, includes detecting, on a point-of-sale (POS) terminal, an event occurrence associated with at least one validation process.
The method may then receive an image from each of at least one camera of a plurality of cameras of the product scanner.
The method further includes processing at least one of the received images according to the at least one validation process to obtain a result and providing the result to the POS terminal.
Date filed: Dec. 13, 2016
Applicants: Quisk, Inc.
Systems and methods for fraud monitoring in a payment service are disclosed.
An exemplary system includes a first server being located at a first locale and routing a first series of transaction requests. The system includes a second server being located at a second locale and routing a second series of transaction requests.
The transactions requests may or may not be associated with a single payment service user account. The system includes a distributed cache storing a set of transaction details of the two series of transaction requests.
The system includes a risk service having access to the set of transaction details from the distributed cache.
The risk service generates a fraud warning based on a result of a comparison of at least one transaction detail in the set of transaction details and at least one transaction detail of a new transaction request received by the first server.
Date filed: Dec. 8, 2016
In one aspect a computerized method for detecting anomalies in expense reports of an enterprise includes the step, of implementing a semantic analysis algorithm on an expense report data submitted by an employee, wherein the expense report data is provided in a computer-readable format.
The method includes the step of, with one or more machine learning algorithms, detecting an anomaly expense report data.
The method includes the step of obtaining an augmentation of the expense report data with a se of web scale data. The method includes the step of verifying receipts associated with an expense report.
The method includes the step of determining that the employee or any employee has previously claimed an expense in the expense report data.
The method includes the step of identifying an inappropriate expense in the expense report data.
Date filed: April 28, 2016
Applicants: Insurance Services Office, Inc.
Inventors: Tamara Costello, Krassimir G. Ianakiev, Janine Johnson
Systems and methods for computerized fraud detection using machine learning and network analysis are provided.
The system includes a fraud detection computer system that executes a machine learning, network detection engine/module for detecting and visualizing insurance fraud using network analysis techniques.
The system electronically obtains raw insurance claims data from a data source such as an insurance claims database, resolves entities and events that exist in the raw claims data, and automatically detects and identify relationships between such entities and events using machine learning and network analysis, thereby creating one or more networks for visualization.
The networks are then scored, and the entire network visualization, including associated scores, are displayed to the user in a convenient, easy-to-navigate fraud analytics user interface on the user's local computer system.
Date filed: March 3, 2016
Applicants: Saraansh Software Solutions PVt. Ltd.
A computer system for detecting banking frauds in historical data and future transactions from a user supplied specimen set of fraudulent transactions.
The proposed fraud system can include:
- a user console that receives a type of fraud and a plurality of known fraudulent banking transactions associated with the type of fraud from the user
- a first set of clue detectors operating on the plurality of known fraudulent banking transactions from the user
- a clue detector archive that stores a second set of clue detectors, wherein each of the stored second set of clue detectors has a score that exceeds a threshold value for each clue detector, and
- a backpropagation neural network that calculates a weight for the stored second set of clue detectors using a learning scheme, wherein a fraud scenario is created based on the stored second set of clue detectors and corresponding weights.
Date filed: March 1, 2016
Assignees: F-Secure Corporation
Methods are detailed for online fraud prevention.
In one approach state information of a first and a second device is monitored, both of which are associated with one user.
During a multi-factor authentication procedure which utilizes at least one of the first and the second devices for authorizing a transaction by an Internet domain, a security server participates in a supplemental security procedure which is conditional on the monitored state information.
In another approach the second device receives a message that is ostensibly related to multi-factor authorization by an Internet domain, and in response sends a query about state information of the first device.
Based on the response to the query that indicates the state information, the second device performs a supplemental security procedure.
Date filed: Dec. 29, 2015
Inventors: Qurio Holdings, Inc.
A system for tracking copyright compliance comprises a database, the database including unique identifiers for a plurality of content capture devices.
The unique identifiers may be obtained from devices prior to the presentation of protectable content, for example, by pre-registration during the process of obtaining a ticket to a performance or at a security checkpoint at an event.
The unique identifiers may be associated with a copyright policy pertaining to content at the event. Each device may embed its unique identifier in content captured by the device, such as via a watermark.
Software may obtain data embedded in content and access the database to determine the copyright status of the content by sending a request including data identifying the capture device.
If content is obtained from an unauthorized source, the content may be traced back to a specific device.
Date filed: Dec. 3, 2015
Applicants: Verizon Patent and Licensing Inc.
Credit card fraud prevention techniques are disclosed in which the authorization of a payment card may be performed using information obtained from a mobile device (e.g., a smart phone) associated with a user who initiates a point-of-sale payment card transaction.
In one implementation, a device may receive a request for authorization of a payment associated with a payment card; and obtain location information relating to a location of a mobile device associated with a user of the payment card.
The device may determine, based at least on a location of the point-of-sale terminal and the location of the mobile device, whether to authorize the request for authorization of the payment.
Date filed: Oct. 8, 2015
Applicants: WaveMarket Inc. (Location Labs)
Inventors: Andrew Weiss, Scott Hotes
A process-based, automated phone fraud management system that operates over a communication network to protect a user from attempted fraud by a fraud agent is disclosed. Local application software interacts with server software to provide alerts for a protected user based on phone numbers known to be, assumed to be, or found to be associated with fraud agents.
The server keeps lists of phone numbers, and searches those lists to classify phone numbers. Phone calls to or from numbers associated with a fraud agent are interrupted. Questionable calls are converted to text and the text is then searched to identify words and phrases commonly associated with phone fraud.
Date filed: Aug. 20, 2015
Applicants: Thomson Reuters Global Resources
Inventors: Ihab Shraim, Mark Shull, James Hepworth
Various embodiments of the invention provide solutions (including inter alia, systems, methods and software) for dealing with online fraud. Some embodiments function to access and/or obtain information from (and/or receive data from) a data source; the data might, for example, indicate a possible instance of online fraud.
Certain embodiments, therefore, can be configured to analyze the data, e.g., to determine whether the data indicate a likely instance of online fraud. Such instances may be further investigated, and/or a response may be initiated. Data sources can include, without limitation, web pages, email messages, online chat sessions, domain zone files, newsgroups (and/or postings thereto), etc.
Data obtained from the data sources can include, without limitation, suspect domain registrations, uniform resource locators, references to trademarks, advertisements, etc.
"Systems and Methods for Monitoring and Detecting Fraudulent Uses of Business Applications."
Date filed: May 5, 2015
Assignees: FIS Financial Compliance Solutions LLC
Applicants: Jwahar R. Bammi, Bagepalli C. Krishna, Robert Posniak, Joseph Walsh
A systems and methods are described detect fraud in existing logs of raw data. There can be several disparate logs, each including data of disparate data types and generated by different and possibly unrelated software enterprise applications.
The fraud management system aggregates and organizes the raw log data, archives the data in a manner that facilitates efficient access and processing of the data, allows for investigation of potentially fraudulent usage scenarios, and uses the results of the investigation to identify patterns of data that correspond to correspond to high risk usage scenarios and/or process steps.
In subsequent processing, archived data can be compared against the identified patterns corresponding to high risk usage scenarios to detect matches, and the invention thereby automatically detects high risk usage scenarios and issues appropriate alerts and reports.
Date Filed: Nov. 10, 2015
Assignees: Microsoft Technology Licensing
Applicants: Thomas Pitcairn Gemmell, Gaurav Kapila, Bahadir B. Onalan, Ashvinkumar J. Sanghvi
Techniques are described herein that are capable of generating a compliance data model for information technology (IT) control. The compliance data model is capable of capturing data from technologies (e.g., software programs, file systems, etc.) and/or developers of those technologies for determining compliance of the technologies with regulations.
The compliance data model may be used to automate generation of artifacts. Each artifact is machine-readable code that includes instructions regarding how to implement a control. A control is a software container that is associated with one or more elements, such as a control objective, a control activity, a control activity test, etc.
The artifacts are usable by management systems to obtain data regarding installed technologies, settings of the technologies, configurations of the technologies, events that are being utilized by the technologies, etc. The management systems may use the data to generate reports regarding compliance of the technologies with the regulations.
"System and Method for Progress Account Opening by Means of Risk-Based Context Analysis"
Date filed: Oct. 29, 2015
Assignees: C1 Bank
Inventors: Marcio deOliveira, Trevor Burgess, Vasyl Borysovych Martyniuk
Systems and methods permit flexible and convenient customer account opening to minimize both customer friction and the risk to financial service providers.
In one embodiment, a computing device associated with a financial service provider receives an account application containing customer information and a request to open a new account or a request to upgrade an existing account.
The computing device performs a verification analysis to validate inputs, authenticate customer identity, ensure compliance with regulatory requirements, or evaluate the risk posed by a customer. The computing device performs a recommendation analysis to determine the appropriate product types and account restrictions that should be offered to a customer, if any.
The computing device creates an account application status message indicating approval or denial of the account application.
Date filed: Oct. 22, 2015
Applicant: Univerys Corp.
Inventors: Craig Allison, Richard Binnendyk
A computer implemented method for generating financial compliance data including generating by a computer system a risk tolerance questionnaire receiving data inputted by a user and stored in a first database on a computer readable medium in communication with the computer system; the risk tolerance questionnaire including data fields representative of a user's financial risk tolerance; generating by the computer system a know-your-client user profile stored in a second database on a computer readable medium in communication with the computer system; and mapping one or more fields from the first database onto one or more fields from the second database, such that the know-your-client user profile is at least partially completed with data obtained from the risk tolerance questionnaire.
Date filed: March 19, 2015
Applicants: Brighterion, Inc.
Inventors: Akli Adjaoute
Real-time fraud prevention software-as-a-service (SaaS) products include computer instruction sets to enable a network server to receive medical histories, enrollments, diagnosis, prescription, treatment, follow up, billings, and other data as they occur.
The SaaS includes software instruction sets to combine, correlate, categorize, track, normalize, and compare the data sorted by patient, healthcare provider, institution, seasonal, and regional norms. Fraud reveals itself in the ways data points deviate from norms in nonsensical or inexplicable conduct.
The individual behaviors of each healthcare provider are independently monitored, characterized, and followed by self-spawning smart agents that can adapt and change their rules as the healthcare providers evolve.
Such smart agents will issue flags when their particular surveillance target is acting out of character, outside normal parameters for them. Fraud controls can therefore be much tighter than those that have to accommodate those of a diverse group.