Abstract: Methods, systems, and computer program products may formulate an iterative data mix up problem into a Markov decision process (MDP) with a tailored reward signal to guide a learning process. To solve the MDP, a deep deterministic actor-critic framework may be modified to adapt a discrete-continuous decision space for training a data augmentation policy.

Abstract: Provided is a system that includes a processor to receive interaction data associated with a plurality of interactions, generate a first intermediate embedding, a second intermediate embedding, and a third intermediate embedding using at least one machine learning model, provide the first intermediate embedding as an input to a gating machine learning model to generate an intermediate classification of the first intermediate embedding, multiply the intermediate classification of the first intermediate embedding, the second intermediate embedding, and the third intermediate embedding to provide an intermediate product of outputs, combine the first intermediate embedding and the intermediate product of outputs to provide a combined final input, and generate an output classification label of the combined final input based on providing the combined final input to a head machine learning model. Methods and computer program products are also provided.

Abstract: Methods, systems, and computer program products may formulate an iterative data mix up problem into a Markov decision process (MDP) with a tailored reward signal to guide a learning process. To solve the MDP, a deep deterministic actor-critic framework may be modified to adapt a discrete-continuous decision space for training a data augmentation policy.

Abstract: Provided are systems, methods, and computer program products for generating node embeddings. The system includes at least one processor programmed or configured to generate a graph comprising a plurality of nodes, generate an embedding for each node of the plurality of nodes, each embedding comprising at least one polar angle and a vector length, store each embedding of a plurality of embeddings in memory, and in response to processing the graph with a machine-learning algorithm, convert at least one embedding of the plurality of embeddings to Cartesian coordinates.

Abstract: Methods, systems, and computer program products for community detection: (i) obtain a plurality of node embeddings associated with a graph; (ii) determine a number of clusters into which the plurality of node embeddings is to be clustered; (iii) cluster, based on distances between pairs of node embeddings, the plurality of node embeddings into the number of clusters until, for each node embedding in each cluster, a node associated with that node embedding is within k-hops in the graph of each other node associated with each other node embedding in that cluster; (iv) reposition centroids of the number of clusters; (v) repeat steps (iii) and (iv) until a first stopping criteria is satisfied; (vi) repeat steps (ii) through (v) until a second stopping criteria that depends on a conductance of a clustering including the number of clusters is satisfied; and (vii) provide the clustering including the number of clusters.

Abstract: Methods and systems are provided for synthesizing realistic time series data that may be used to better identify outliers within the synthesized realistic time series data. Noise can be introduced to a time domain representation of time series data and can introduce noise to a frequency domain representation of the time series data. Further, labeled anomalous points can be inserted into the time series data. The time series data may then be used for training a machine learning model to identify anomalies within new time series data.

Abstract: Systems, methods, and computer program products are provided for predicting a specified geographic area of a user. An example system includes a processor configured to determine a verified geographic area associated with each user, and determine a feature vector associated with an account of each user. The processor is also configured to receive transaction data and determine a value of each parameter of the feature vector for each user based on the transaction data to produce a training matrix. The processor is further configured to train and validate a geographic area prediction model based on the training matrix. The processor is further configured to repeatedly generate a prediction that a user will conduct a transaction in a geographic area, communicate an offer to the user based on the prediction, receive new training data, and update the geographic area prediction model based on the new training data.

Abstract: Provided are computer-implemented methods for generating embeddings for objects which may include receiving heterogeneous network data associated with a plurality of objects in a heterogeneous network; selecting at least one pattern of objects; determining instances of each pattern of objects based on the heterogeneous network data; generating a pattern matrix for each pattern of objects based on the instances of the pattern of objects; generating pattern sequence data associated with a portion of each pattern matrix; generating network sequence data associated with a portion of the heterogeneous network data; and combining the pattern sequence data and the network sequence data into combined sequence data. In some non-limiting embodiments or aspects, methods may include generating a vector for each object of the plurality of objects based on the combined sequence data. Systems and computer program products are also provided.

Abstract: Methods, systems, and computer program products may formulate an iterative data mix up problem into a Markov decision process (MDP) with a tailored reward signal to guide a learning process. To solve the MDP, a deep deterministic actor-critic framework may be modified to adapt a discrete-continuous decision space for training a data augmentation policy.

Abstract: Provided is a system, method, and computer program product for predicting a specified geographic area of a user. The method includes receiving transaction data associated with a plurality of transactions during a predetermined time interval. The method also includes generating a geographic area prediction model based on the transaction data by determining a verified geographic area for each user, and determining transaction data associated with a plurality of transactions involving each user for a plurality of feature vector parameters, training the geographic area prediction model based on the plurality of feature vector parameters for the verified geographic area for each user, and validating the geographic area prediction model based on the plurality of feature vector parameters for the verified geographic area for each user.

Abstract: Described are a system, method, and computer program product for applying deep learning analysis to predict and automatically respond to predicted changes in financial device primacy for a financial device holder. The method includes receiving transaction data representative of a plurality of transactions between the financial device holder and at least one merchant. The method also includes generating time series data based on the transaction data and generating a predictive model configured to: (i) receive an input of time-interval-based transaction data; and (ii) output a probability of primary financial device primacy change, the predictive model trained based on historic transaction data. The method further includes determining a probability of primary financial device primacy change for the financial device holder by applying the predictive model to the time series data. The method further includes, generating at least one communication to at least one issuer and/or the financial device holder.

Abstract: Methods, systems, and computer program products are provided for optimizing training loss of a graph neural network machine learning model using bi-level optimization. An example method includes receiving a training dataset comprising graph data associated with a graph, training a graph neural network (GNN) machine learning model using a loss equation according to a bi-level optimization problem and based on the training dataset, where training the GNN machine learning model using the loss equation according to the bi-level optimization problem includes determining a solution to an inner loss problem and a solution to an outer loss problem, and providing a trained GNN machine learning model based on training the GNN machine learning model.

Abstract: Provided are computer-implemented methods for generating embeddings for objects which may include receiving heterogeneous network data associated with a plurality of objects in a heterogeneous network; selecting at least one pattern of objects; determining instances of each pattern of objects based on the heterogeneous network data; generating a pattern matrix for each pattern of objects based on the instances of the pattern of objects; generating pattern sequence data associated with a portion of each pattern matrix; generating network sequence data associated with a portion of the heterogeneous network data; and combining the pattern sequence data and the network sequence data into combined sequence data. In some non-limiting embodiments or aspects, methods may include generating a vector for each object of the plurality of objects based on the combined sequence data. Systems and computer program products are also provided.

Abstract: Provided is a computer-implemented method for generating synthetic graphs that simulate real-time payment transactions that includes generating a base payment graph includes a plurality of nodes and a plurality of edges connecting the plurality of nodes, wherein each node represents an entity and each edge represents a probability that a real-time-payment transaction may be conducted involving two entities that are connected by the edge, wherein the real-time payment transaction is artificially created, generating a plurality of dynamic payment graphs based on the base payment graph, inserting patterns representing adversarial activity into the plurality of dynamic payment graphs, and performing an action associated with a machine learning technique using the plurality of dynamic payment graphs. Systems and computer program products are also provided.

Abstract: Apparatuses, methods, and systems are provided for making sequential recommendations using transition regularized non-negative matrix factorization. A non-application specific collaborative filtering based personalized recommender system can recommend a next logical item from a series of related items to a user. The recommender system can recommend a next desirable or series of next desirable new items to the user based on the historical sequence of all user-item preferences and a user's most recent interaction with an item. An asymmetric item-to-item transition matrix can capture aggregate sequential user-item interactions to design a loss function for matrix factorization that incorporates the transition information during decomposition into low-rank factor matrices.

Abstract: Provided are systems, methods, and computer program products for generating node embeddings. The system includes at least one processor programmed or configured to generate a graph comprising a plurality of nodes, generate an embedding for each node of the plurality of nodes, each embedding comprising at least one polar angle and a vector length. store each embedding of a plurality of embeddings in memory, and in response to processing the graph with a machine-learning algorithm, convert at least one embedding of the plurality of embeddings to Cartesian coordinates.

Abstract: Described are a system, method, and computer program product for applying deep learning analysis to predict and automatically respond to predicted changes in financial device primacy for a financial device holder. The method includes receiving transaction data representative of a plurality of transactions between the financial device holder and at least one merchant. The method also includes generating time series data based on the transaction data and generating a predictive model configured to: (i) receive an input of time-interval-based transaction data; and (ii) output a probability of primary financial device primacy change, the predictive model trained based on historic transaction data. The method further includes determining a probability of primary financial device primacy change for the financial device holder by applying the predictive model to the time series data. The method further includes, generating at least one communication to at least one issuer and/or the financial device holder.

Abstract: Described are a system, method, and computer program product for applying deep learning analysis to predict and automatically respond to predicted changes in financial device primacy for a financial device holder. The method includes receiving transaction data representative of a plurality of transactions between the financial device holder and a merchant. The method also includes generating time series data based on the transaction data and generating a predictive model configured to: (i) receive an input of time-interval-based transaction data; and (ii) output a probability of primary financial device primacy change, the predictive model trained based on historic transaction data. The method further includes determining a probability of primary financial device primacy change for the financial device holder by applying the predictive model to the time series data. The method further includes, generating at least one communication to at least one issuer and/or the financial device holder.

Abstract: A non-transitory computer readable medium can store machine readable instructions that when accessed and executed by a processing resource cause a computing device to perform operations. The operations can include establishing a connection between data stores (such as a relational data store and a graph engine), wherein the connection includes a shared memory buffer storing data in a data format according to internal structures of the graph engine. The connection between the data stores is bi-directional. The connection enables data that is stored in the shared memory to be processed by either of the graph engine and the relational database. Upon receiving a query, the graph engine or the relational database can be selected to process the data based on a query. The data can be processed by the selected one of the graph engine or the relational database.

Abstract: Provided are computer-implemented methods for generating embeddings for objects which may include receiving heterogeneous network data associated with a plurality of objects in a heterogeneous network; selecting at least one pattern of objects; determining instances of each pattern of objects based on the heterogeneous network data; generating a pattern matrix for each pattern of objects based on the instances of the pattern of objects; generating pattern sequence data associated with a portion of each pattern matrix; generating network sequence data associated with a portion of the heterogeneous network data; and combining the pattern sequence data and the network sequence data into combined sequence data. In some non-limiting embodiments or aspects, methods may include generating a vector for each object of the plurality of objects based on the combined sequence data. Systems and computer program products are also provided.