Visa International Service Association

Cybersource Corporation

Benjamin Scott Boding

Haochuan Zhou

Hung-Tzaw Hu

Cory Howard Siddens

Ge Wen

Andrew John Bruno Naumann Zu Koenigsbrueck

Rong Zhang

Nathan Ryan Wood

Carl David Tucker, Jr

Christopher Holmes

Ali Chamseddine

Henry Wong

Jianjie Ma

Shawna Bushart

Systems and methods are described for pre-authentication access request screening. A server computer may receive a request for access to a resource comprising access data. The server computer may transmit, to an authentication computer, an authentication request message comprising at least a subset of the access data and receive an authentication response message comprising authentication data. The server computer may determine an access score based on the authentication data. Alternatively, the server computer may determine the access score based on the access data without using/receiving authorization data. The server computer may generate an access indicator based on the access score. The server computer may prepare and transmit an authorization request message comprising the access indicator to an authorization computer. The authorization computer may approve or decline the access to the resource based on the access indicator.

Pre-authorization access request screening

Embodiments of the present disclosure provide systems, methods, and apparatuses for addressing the above problems through the use of access rules that involve analyzing historical access request result data for various data elements individually and in combination over a predefined time interval. An automated determination can be made for whether a transaction can be authenticated based upon the historical access request result data (e.g., ultimately, deciding whether the data element or set of data elements are associated with a valid access request).

Real-time access rules using aggregation of periodic historical outcomes

Provided is a method for configuring at least one rule, e.g., using a graphical user interface. The method may include displaying a graphical user interface including a polygon having at least three edges and an icon at a first position within the polygon. Each edge of the polygon may be associated with a potential outcome of at least one rule. An input to move the icon to a second position within the polygon may be received. The graphical user interface may be displayed with the icon at the second position within the polygon. A distance from the second position of the icon to each edge of the polygon may be determined. The rule(s) may be adjusted based on the distance from the second position of the icon to each edge of the polygon. A system and computer program product are also disclosed.

Method, system, and computer program product for configuring at least one rule via a graphical user interface

Techniques managing access rules are provided. Access rules and their associated profiles are determined for evaluation. A triggering rate or a triggering percentage can be used to indicate efficacy of the rule. Recommendations can be provided based on a triggering percentage difference of the rule during a predetermined period of time. The recommendations can be provided in an interactive user interface.

Access rule management

Disclosed is a system to optimize rule weights for classifying access requests so as to manage rates of false positives and false negative classifications. A rules suggestion engine may suggest a profile of classification rules to a merchant for access requests. The system can optimize weights for the profile of rules using a cost function based on a training set of historical access requests, for example using stepwise regression or machine learning (ML). The system can compute a profile score based on the optimized weights, for example by summing the weights. The system statistically analyzes the profile score using classification thresholds and the historical access requests. The system can perform receiver operating characteristic (ROC) analysis for various threshold values, enabling a user to select a suitable threshold. The system can further optimize by adding or removing rules from the profile of rules.

Auto-tuning of rule weights in profiles

Techniques for managing redundant or overlapping access rules are provided. Access rules are determined for evaluation. Performance metrics for the access rules prior to implementation and post implementation are determined. Overlapping access rules are identified. Performance of the overlapping access rules are evaluated to determine actions to be applied to the overlapping access rules. Recommended actions and adjustments can be automatically provided by the system based on the performance analysis.

Techniques for redundant access rule management

Resources can be secured by a resource security system. The resource security system can determine whether to grant or deny access to resources using authorization information in an access request. The resource security system can also determine whether the access request is legitimate or fraudulent using risk scoring models. A score transformation table can be used to provide consistency in the risk level for a particular score over time. The score transformation table can be based on a target score profile and a precision format (e.g., integer or floating point). The score transformation table can dynamically adapt based on the trending top percent of risk and can account for changes in the distribution of scores over time or by weekday. The scores can be used to determine an access request outcome. Access to the resource can be accepted or rejected based on the outcome.

Systems and methods for determining access outcomes using access request scoring

Described are a system, method, and computer program product for optimizing a predictive condition classification model and automatically enacting reactive measures based thereon. The method includes receiving event data representative of a plurality of events. The method also includes receiving the predictive condition classification model configured to categorize each event as satisfying a condition or not. The predictive condition classification model is configured to order the plurality of events by likelihood of satisfying the condition. The method includes generating a performance evaluation dataset and plotting data configured to cause a visual display to represent at least two model performance metrics of the performance evaluation dataset on a same output plot. The method includes automatically rejecting a top percent of the plurality of events for suspected satisfaction of the condition, determined at least partially from a customized rejection algorithm or a preset rejection algorithm.

Growing community of inventors

Mountain View, CA, United States of America

Benjamin Scott Boding