Abstract: A method for optimizing invoice payments according to supplier and buyer controls includes: receiving one or more received data message including invoice data, a buyer identification value, a supplier identification value, and a plurality of buyer optimization priorities, wherein the invoice data is associated with an invoice and includes an invoice amount and due date; identifying a plurality of supplier controls associated with the supplier identification value; identifying one or more buyer preferences associated with the buyer identification value; determining an optimal payment schedule for one or more payment transactions for the invoice based on the invoice data, the buyer optimization priorities, the plurality of supplier controls, and the one or more buyer preferences; transmitting a transmitted data message including the determined optimal payment schedule.

Abstract: Systems and computer-implemented methods are described for modeling card inactivity. For example, hierarchical modeling may be used in which a first level classifier may be trained and validated to predict whether a card will be inactive. For cards predicted to become inactive by the first level classifier, a second level classifier may be trained and validated to predict when the card will become inactive. The first level classifier may include a binary classifier that generates two probabilities that respectively predict that the card will and will not become inactive. The second level classifier may include a multi-class classifier that generates a first probability that the card will become inactive at a first time period (such as one or more months in the future) and a second probability that the card will become inactive at a second time period. The multi-class classifier may generate other probabilities corresponding to other time periods.

Abstract: A fraud prevention server that includes an electronic processor and a memory. The memory includes an online application origination (OAO) service and a plurality of OAO models, each of the plurality of OAO models differentiates between a behavior of a normal user and a behavior of a nefarious actor during a submission of the online application on a device. When executing the OAO service, the electronic processor is configured to receive form data from a client server, determine a best OAO model from a plurality of OAO models with deep-learning, determine a fraud score of the online application based on the best OAO model, and control the client server to approve, hold, or deny the online application based on the fraud score that is determined.

Abstract: Embodiments provide methods and systems for unsupervised representation learning for bipartite graphs. Method performed by server system includes accessing historical transaction data from database. Method includes generating a bipartite graph based on historical transaction data. Bipartite graph represents a computer-based graph representation of a plurality of cardholders as first nodes and a plurality of merchants as second nodes and payment transactions between first nodes and second nodes as edges. Method includes sampling direct neighbor nodes and skip neighbor nodes associated with a node based on neighborhood sampling method and executing direct neighborhood aggregation method and skip neighborhood aggregation method to obtain direct neighborhood embedding and skip neighborhood embedding associated with node, respectively.

Abstract: A fraud prevention server that includes an electronic processor and a memory. The memory includes an online application origination (OAO) service and a plurality of OAO models, each of the plurality of OAO models differentiates between a behavior of a normal user and a behavior of a nefarious actor during a submission of the online application on a device. When executing the OAO service, the electronic processor is configured to receive form data from a client server, determine a best OAO model from a plurality of OAO models with deep-learning, determine a fraud score of the online application based on the best OAO model, and control the client server to approve, hold, or deny the online application based on the fraud score that is determined.

Abstract: A computing device for analyzing data from user spending patterns to determine offers to be presented to credit card customers comprises a processing element configured to: receive transaction data for a plurality of transactions for each of a plurality of credit card numbers; input the transaction data into an encoder that performs linear transformations and nonlinear transformations to produce latent space data with each latent space data point being associated with one credit card number; input the latent space data into a clustering element which associates each credit card number with one of a plurality of clusters; and make an upgrade offer to credit card numbers that have a normal credit status and which are associated with clusters that include credit card numbers that have a preferred credit status.

Abstract: A method of managing a controller of a software defined networking (SDN) network is implemented by a computing device in the SDN network. The method includes receiving status information for the controller, receiving usage information for the operating environment, generating at least one failure prediction for the controller based on the received status information, and outputting prediction information for the at least one failure prediction.

Abstract: Embodiments provide methods and systems for predicting panic situation in a region and detecting panic states of merchants in the region. Method performed by server system includes accessing payment transaction data associated with merchants from transaction database and identifying panic trigger indicating panic situation in region based on transaction features associated with merchants. In response to identifying panic trigger, method includes generating transaction features based on payment transactions of merchant over time duration and determining association between merchant and merchant cluster based on transaction features associated with merchant. Method includes predicting time-series transaction data associated with merchant based on deep neural network model and merchant cluster associated with merchant, and calculating error between predicted time-series transaction data and real time-series transaction data associated with merchant.

Abstract: Embodiments provide methods and systems for determining prospective acquisitions among business entities using machine learning techniques. Method performed by server system includes accessing financial data items and news items associated with finances of business entities from data sources for particular time duration. Method includes generating financial and news feature vectors corresponding to business entities and applying machine learning models over financial feature vectors and news feature vectors associated with business entities for determining candidate set of business entities predicted to be engaged in business acquisition in future. Method includes creating dynamic bipartite knowledge graph for each distinct time durations within particular time duration and generating static bipartite knowledge graph based on dynamic bipartite knowledge graphs for distinct time durations.

Abstract: Embodiments provide methods and systems for predicting merchant level health intelligence. Method performed by server system includes accessing, from a transaction database, payment transaction data of a merchant for a period of time. The payment transaction data includes information of payment transactions between a plurality of cardholders and the merchant for the period of time. The method includes aggregating merchant transaction attributes based, at least in part, on the payment transaction data and calculating a merchant membership vector based, at least in part, on the merchant transaction attributes by applying a soft-clustering model over the merchant transaction attributes. The method further includes predicting a commercial credit score and a merchant delinquency rate associated with the merchant based, at least in part, on the merchant membership vector. The commercial credit score and the merchant delinquency rate are predicted based, at least in part, on a multi-task learning model.

Abstract: Systems and methods are provided for determining an environmental impact of one or more transactions. An example method generally includes accessing transaction data representative of a plurality of transactions, where each of the transactions involves a user and a merchant, and accessing at least one index indicative of environmental impact of a plurality of merchants. The method also includes generating a graph based on the users and merchants included in the transaction data, whereby the graph is representative of the plurality of transactions, and determining a mapping between ones of the merchants involved in the transaction data and the environmental impact indicated by the at least one index, based on at least one of: the graph, the accessed at least one index, a graph convolution network (GCN), and a graph neural network (GNN). The method then includes publishing the mapping between the ones of the merchants and the environmental impact.

Abstract: Systems and computer-implemented methods are described for modeling card inactivity. For example, hierarchical modeling may be used in which a first level classifier may be trained and validated to predict whether a card will be inactive. For cards predicted to become inactive by the first level classifier, a second level classifier may be trained and validated to predict when the card will become inactive. The first level classifier may include a binary classifier that generates two probabilities that respectively predict that the card will and will not become inactive. The second level classifier may include a multi-class classifier that generates a first probability that the card will become inactive at a first time period (such as one or more months in the future) and a second probability that the card will become inactive at a second time period. The multi-class classifier may generate other probabilities corresponding to other time periods.

Abstract: Systems and computer-implemented methods of modeling card member data to classify a card member into one of a plurality of classifications based on interchange fees derived from the use of a card issued to the card member. The modeling may handle data distribution from one time period to another time period to address unavailability and/or variability of historical data, implement a neural network architecture based on transformers and discriminators for accurate data scaling, perform data filling for missing data, and fine-tuning for card types that have less card member data, which may result in enhanced performance and faster convergence resulting in reduced computational time. Such fine-tuning may leverage uniform standardization in the neural network to handle multiple card types, which is facilitated through the use of the transformers and discriminators for data scaling.

Abstract: Aspects of the disclosure provide a computerized method and system that utilizes reference expense reports to build and train one or more neural network learning models that intelligently determine the riskiness of to-be-determined expense reports submitted for reimbursement. In examples, a determined riskiness may inform a reimbursement entity manager when determining whether to approve, reject, and/or flag for further review a to-be-determined expense report. In instances, computerized expense report resolution systems and methods may be further automated in order to omit user interactions with to-be-determined expense reports, such that an intelligent computer determines whether to approve, reject, and/or flag a to-be-determined expense report based on the intelligently determined riskiness of the to-be-determined expense report.

Abstract: An aspect of the present disclosure aids further examination of data set for improving corresponding key performance indicators (KPI). In an embodiment, a data set containing a plurality of data points is selected, with each data point specifying an individual fact value for a respective combination of members and each member being associated with a corresponding dimension. A respective aggregate fact value is generated for each member of each dimension. A respective variation among aggregate fact values of corresponding members is computed for each dimension. The set of dimensions having more variation is identified as containing pertinent information for further examination of a key performance indicator (KPI).

Abstract: A BI system identifies key performance indicators (KPIs) of interest for a given time duration without requiring any user inputs for such purpose. In other words, the user may provide inputs for purposes such as specifying the time duration, for initiation of execution of modules to trigger the identification, etc., but no user inputs may be required for such identification itself. In an embodiment, the KPIs of interest are determined by examining a corresponding sequence of measurements for each key performance indicator (KPI). The KPIs thus identified are sent for display.