Abstract: Embodiments of the invention are directed to a fraud detection system that stores fraud detection rules and merchant profiles. The fraud detection system allows a user to designate fraud detection rules as core fraud detection rules, and the fraud detection system can automatically populate new merchant profiles with the user's core fraud detection rules.

Abstract: In some embodiments, a resource security system may determine an access request outcome (e.g., accept, reject, or review) for an access request based on access rules. The resource security system may generate and select the access rules to be used for using stability information. For instance, the resource security system may select a training set from the received access requests, e.g., including recently received access requests, and generate a plurality of potential access rules based on the training set. The resource security system may determine and compare the detection performance and the stability performance of the potential access rules. The resource security system may select the best performing potential access rules to be used in operation for determining the outcome of access requests.

Abstract: Embodiments of the invention are directed to a fraud detection system that stores fraud detection rules and merchant profiles. The fraud detection system allows a user to designate fraud detection rules as core fraud detection rules, and the fraud detection system can automatically populate new merchant profiles with the user's core fraud detection rules.

Abstract: Embodiments of the invention generally relate to methods and systems for operating authorization rules. An authorization rule has conditions that may be satisfied by an authorization request. A rule is rotated between the first mode and the second mode over a time interval wherein a first set of authorization requests are received. A first subset of the first set of authorization requests may not be rejected. After the first time interval, the authorization requests that were not rejected may be validated through an independent process. An accuracy rate for the rule is determined based on the portion of authorization requests that are valid and satisfied the conditions of the rule.

Abstract: Embodiments of the invention are directed to a fraud detection system that stores fraud detection rules and merchant profiles. The fraud detection system allows a user to designate fraud detection rules as core fraud detection rules, and the fraud detection system can automatically populate new merchant profiles with the user's core fraud detection rules.

Abstract: Embodiments of the present invention are directed to methods and systems for performing a secure authentication process by leveraging the historical transaction data associated with an issuer. The historical transaction data stored at a fraud detection system may include the types of frequency of past authentication processes performed by the issuer, allowing for a determination of the likelihood of an authentication challenge process being applied to a current transaction. A merchant may define merchant rules that define what authentication process, if any, should then be applied to the current transaction based on the likelihood of an authentication challenge process being applied to the current transaction.

Abstract: Embodiments of the invention are directed to a fraud detection system that records an audit log of modifications made by a user to a selection of fraud detection rules in a merchant profile. The audit log contains details of the modifications and the user associated with the modifications. A search can be conducted on the audit log to determine details of modifications made to a merchant profile within the fraud detection system.

Abstract: Embodiments of the invention are directed to systems, apparatus, and methods for preventing merchant fraud by processing electronic payment transactions using acquirer rules. In some embodiments, a server computer can receive from an acquirer a rule to be applied to transactions conducted with a merchant. A plurality of authorization messages (e.g., request or response messages) can be received, each corresponding to a different transaction conducted with the merchant. An aggregate value can be calculated based on transaction data included in the authorization messages. It can be determined whether the aggregate value triggers the rule. If the rule is triggered, a transaction can be processed in accordance with a first protocol (e.g., by declining authorization or by withholding a settlement amount). If the rule is not triggered, the transaction can be processed in accordance with a second protocol (e.g., by proceeding with the transaction or releasing the full settlement amount).

Abstract: Embodiments of the invention are directed to systems and methods for implementing a rules suggestion engine that suggests rules to a user for lowering fraud in future transactions. Embodiments of the invention segment the transaction data based on at least one attribute defined by the user. One or more key indicators are identified corresponding to the segmented data. A correlation is performed between the user defined attribute and one or more key indicators. One or more transaction rules are generated based on the correlation that are suggested to the user for future transactions. The user can customize the rule, a field of rule, a prioritization of the rules, and even create categories of rules.

Abstract: Embodiments of the invention are directed to computer that can utilize a first computer and a second computer. The first computer may determine a first fraud score based on transaction data. If the first fraud score is indeterminate, the transaction may be assigned to a transaction review queue. If the subsequent review takes too long to complete, then a second computer may be used to compute a second fraud score to determine an outcome for the transaction.

Abstract: Systems and methods for testing new profiles and rules against past transaction data in a quick manner are provided. A set of transactions is identified by a merchant based on a selection criterion that is replayed against the new profile. Results of the replay are recorded and compared against the original results obtained from applying an existing profile to the same set of transaction data. A tic-tac-toe report is generated for the merchant showing shifts in transaction results between the existing profile and the new profile. Embodiments of the invention further allow merchants to generate multiple scores, in parallel, against different transaction models using knobs or hedges.

Abstract: Embodiments of the invention are directed to systems and methods for implementing a rules suggestion engine that suggests rules to a user for lowering fraud in future transactions. Embodiments of the invention segment the transaction data based on at least one attribute defined by the user. One or more key indicators are identified corresponding to the segmented data. A correlation is performed between the user defined attribute and one or more key indicators. One or more transaction rules are generated based on the correlation that are suggested to the user for future transactions. The user can customize the rule, a field of rule, a prioritization of the rules, and even create categories of rules.

Abstract: Embodiments of the invention broadly described, introduce systems and methods for detecting the likelihood that a transaction is fraudulent using user access pattern data and device fingerprint data. One embodiment of the invention discloses a method for determining the likelihood that a payment transaction is fraudulent. The method comprises receiving user access pattern data generated by a user client computer, receiving a device fingerprint associated with the user client computer conducting a payment transaction, determining, using the user access pattern data and the device fingerprint, a likelihood that the payment transaction is fraudulent.

Abstract: Embodiments of the invention generally relate to methods and systems for generating rule profile reports, the rule profile reports comprising statistical data regarding the performance of rules. One embodiment of the invention discloses a method for generating a rule profile report. The method comprises determining, by a processor, a rule profile, wherein the rule profile comprises a plurality of rules, and wherein each rule in the plurality of rules is associated with a plurality of rule outcomes, determining for the plurality of rules a plurality of rule outcome frequencies associated with the plurality of rule outcomes, wherein each rule outcome in the plurality of rule outcomes is associated with an outcome for a transaction, and providing, by the processor, the plurality of rule outcome frequencies.

Abstract: In an embodiment, a data processing method comprises obtaining a plurality of first transaction data items for a proposed online credit card purchase transaction that has been recommended for review; obtaining a plurality of second transaction data items for a set of similar past online credit card purchase transactions, wherein each member of the set has one or more transaction feature values that are similar to the transaction data items of the proposed online credit card purchase transaction, and a decision value specifying whether the member was accepted or rejected by a reviewer; obtaining a stored data model of features, feature values, transaction acceptance decisions and rejection decisions of the reviewer based at least in part on the set, determining, based on applying the first transaction data items to the stored data model and a subsequent query to the database among more recent transactions that were not included during model construction, a likelihood value of a particular decision of whether t

Abstract: Embodiments of the invention relate to methods, apparatuses, and systems for performing, creating, generating, and displaying transaction scorecards related to fraud evaluations of transactions. Methods may include determining if one or more preselected rules are triggered by transaction data associated with a transaction, determining a trigger score for each of the preselected rules, adding the trigger score for each of the preselected rules to a profile score, applying the profile score to at least one transaction decision rule, and displaying transaction evaluation results in a transaction scorecard. Additionally, some embodiments of the invention may combine a centralized multiple merchant fraud model provided by a merchant processor and a merchant customized model, to a produce a hybrid scorecard model. The respective scores of the multiple merchant fraud model and the merchant customized model may be weighted for further customization.

Abstract: An identity chaining fraud detection method that allows each current transaction to be linked to other transactions through commonly shared identities. Over a period of time the links create a chain of associated transactions which can be analyzed to determine if identity variances occur, which indicates that fraud is detected. Additionally, if a specific identity is detected as being fraudulent, that identity can be tagged as fraudulent and can be referenced by a plurality of other merchant transaction chains to determine fraud.

Abstract: Modern technologies of signal processing and real-time feedback adaptive control are applied to a fraud screen model to enable the fraud screen model to adapt to changes in shopping behavior to effectively maintain the model's performance on a review rate score curve continuously. Multiple techniques disclosed herein integrate control technologies with modeling technology to control the review rate score curve in real time.

Abstract: Embodiments of the invention are directed to systems and methods for implementing a rules suggestion engine that suggests rules to a user for lowering fraud in future transactions. Embodiments of the invention segment the transaction data based on at least one attribute defined by the user. One or more key indicators are identified corresponding to the segmented data. A correlation is performed between the user defined attribute and one or more key indicators. One or more transaction rules are generated based on the correlation that are suggested to the user for future transactions. The user can customize the rule, a field of rule, a prioritization of the rules, and even create categories of rules.

Abstract: Modern technologies of signal processing and real-time feedback adaptive control are applied to a fraud screen model to enable the fraud screen model to adapt to changes in shopping behavior to effectively maintain the model's performance on a review rate score curve continuously. Multiple techniques disclosed herein integrate control technologies with modeling technology to control the review rate score curve in real time.