Abstract: A new approach is proposed that contemplates systems and methods to support distributed electronic payment processing based on a hierarchical payment graph. Specifically, a distributed electronic payment system comprising a plurality of distributed payment engines/processors. Upon receiving an electronic payment request from a client device, each distributed payment engine of the distributed electronic payment system is configured to handle one stage of the electronic payment processing lifecycle by traversing states and edges in a portion of the hierarchical payment graph assigned to the distributed payment engine.

Abstract: A new approach is proposed to support instant merchant activation for secured in-person payment at a point of sale (POS) of a merchant. When a customer initiates an in-person payment request at a payment initiation device associated with the merchant, the payment initiation device collects both sensitive and non-sensitive portions of electronic payment transaction data for the request and encrypts the sensitive data portion for secured transmission. A payment gateway in the payment transaction process relays the data and the payment request to a payment processor for approval by an issuer and transmits only the non-sensitive portion of the data to a payment service engine for risk analysis if the payment request is approved by the issuer. The payment service engine determines if the payment request is at high risk based on risk analysis of non-sensitive portion of the data and notifies the payment initiation device and/or merchant accordingly.

Abstract: A approach is proposed to support typed payment graph-based electronic payment processing. First, schemas for one or more typed payment graphs used for a plurality types of electronic payment processing are defined declaratively. Upon receiving an electronic payment request from a client, a payment processing engine retrieves a schema of a typed payment graph corresponding to the request and processes the electronic payment by traversing states and edges in an instance created from the schema of the typed payment graph. The electronic payment only transitions from one state to another if a valid edge exists between them and a precondition on the edge is met by the processing results of the electronic payment at the state. While processing the electronic payment, the payment processing engine automatically generates an audit trail for the electronic payment based on its states and transitions for real time recovery and/or analysis.

Abstract: A new approach is proposed that contemplates systems and methods to support streaming aggregation for analysis of electronic transactions. First, a plurality of metrics to be measured/analyzed for a stream of real life events, such as processing steps of the electronic transactions are defined and converted to one or more generic metrics for aggregation. In some embodiments, the plurality of metrics flexibly include ad-hoc aggregation measures as well as various user-defined functions (UDFs), which allow a user/processor/evaluator of the electronic transactions to define and collect various types of information of the electronic transactions for analysis. Once converted, the generic metrics of the stream of real life events are aggregated by an aggregation engine in real time. The aggregation results are then saved in an aggregation database, which is queried by the user for real time analysis of the electronic transaction.

Abstract: A new approach is proposed to support two variants of the approach to effectively generate reason codes for an ensemble model. Both variants involve treating the ensemble model as a black box, identifying trivial values for input variables to the ensemble model, replacing each of the input variables to the ensemble model with its corresponding trivial values and then evaluating the impact on a score of the model after the trivial value replacement. The evaluation result of the impact is then used to generate the reason codes for the ensemble model. Specifically, the first variant is configured to perform one round of replacement, wherein variables with top drops in the score will be the reason codes. The second variant is configured to perform multiple rounds of replacement, which in each round, keeps the identified reason codes variables replaced with trivial values and analyzes incremental drops of replacing remaining variables.

Abstract: A system includes one or more client members connected to one or more primary users and/or one or more end users. The client member receives risk data from the primary user and the end user, and the risk data includes one or more risk variables. A service provider is connected to the client member, and receives at least one of the risk variables from the client member and identifies whether the risk variable corresponds to an undefined type value or a predefined type value. The service member updates an existing database by storing the risk variable under a non-standard type category when the risk variable is identified as the undefined type value. The service member determines whether the received risk variable is a viable risk and a notification is transmitted to the client member when the viable risk is determined.

Abstract: A system includes a computing device that receives risk variables associated with risk data and that associates the risk variables with a plurality of nodes such that each of the risk variables corresponds to a separate node. The computing device analyzes the nodes to identify a level of consistency or a level of inconsistency for each of the nodes and creates a plurality of links such that each of the links connects a separate node with at least one associated related node. The computing device uses each of the links to record data related to the level of consistency or the level of inconsistency identified for the corresponding connected nodes, wherein each of the links corresponds to separate recorded data. The computing device provides a score for each of the links based on the corresponding recorded data and determines the threat of a viable risk based on the provided score.

Abstract: A system includes one or more client members connected to one or more primary users and/or one or more end users. The client member receives risk data from the primary user and the end user, and the risk data includes one or more risk variables. A service provider is connected to the client member, and receives at least one of the risk variables from the client member and identifies whether the risk variable corresponds to an undefined type value or a predefined type value. The service member updates an existing database by storing the risk variable under a non-standard type category when the risk variable is identified as the undefined type value. The service member determines whether the received risk variable is a viable risk and a notification is transmitted to the client member when the viable risk is determined.

Abstract: A new approach is proposed that contemplates systems and methods to support user identity verification based on social and personal information of the user. Under the approach, customers/users are required to grant identity verifying party a degree of access to their social network information, including but not limited to, account data and social graph information on social networks. The identity verifying party then acquires information of a current or potential user's online presence in addition to other information of the user and utilizes such information to verify the user's identity in the real world and/or to assess the fraud risk of a specific financial transaction requested by the user.