Abstract: Systems, methods, and computer program products to provide neural embeddings of transaction data. A network graph of transaction data based on a plurality of transactions may be received. The network graph of transaction data may define relationships between the transactions, each transaction associated with at least a merchant and an account. A neural network may be trained based on training data comprising a plurality of positive entity pairs and a plurality of negative entity pairs. An embedding function may then encode transaction data for a first new transaction. An embeddings layer of the neural network may determine a vector for the first new transaction based on the encoded transaction data for the first new transaction. A similarity between the vectors for the transactions may be determined. The first new transaction may be determined to be related to the second transaction based on the similarity.

Abstract: Systems, methods, and computer program products to provide neural embeddings of transaction data. A network graph of transaction data based on a plurality of transactions may be received. The network graph of transaction data may define relationships between the transactions, each transaction associated with at least a merchant and an account. A neural network may be trained based on training data comprising a plurality of positive entity pairs and a plurality of negative entity pairs. An embedding function may then encode transaction data for a first new transaction. An embeddings layer of the neural network may determine a vector for the first new transaction based on the encoded transaction data for the first new transaction. A similarity between the vectors for the transactions may be determined. The first new transaction may be determined to be related to the second transaction based on the similarity.

Abstract: Systems, methods, and computer program products to provide credit decisioning based on graph neural networks. A lending network graph of a plurality of loans may be received, each loan associated with a creditor and one account. A first node of the graph may be associated with a first creditor and the second node may be associated with a first account. A graph neural network may receive a respective message from each node connected to the first node, each message comprising an embedding vector reflecting a current state of the node. The graph neural network may update weights for the first node in a forward pass. The graph neural network may receive a respective message from each node connected to the second node, each message comprising the embedding vector reflecting the current state of the node. The graph neural network may update weights for the second node in a backward pass.

Abstract: Systems, methods, and computer program products to provide credit decisioning based on graph neural networks. A lending network graph of a plurality of loans may be received, each loan associated with a creditor and one account. A first node of the graph may be associated with a first creditor and the second node may be associated with a first account. A graph neural network may receive a respective message from each node connected to the first node, each message comprising an embedding vector reflecting a current state of the node. The graph neural network may update weights for the first node in a forward pass. The graph neural network may receive a respective message from each node connected to the second node, each message comprising the embedding vector reflecting the current state of the node. The graph neural network may update weights for the second node in a backward pass.

Abstract: Methods and systems are described herein for generating updated sets of attributes that would turn a negative decision of an automated system into a positive decision. A received set of attributes associated with a negative decision of an automated system may be used to generate a latent representation of that set of attributes. A machine learning model may then be used to output a change value (an alpha value). The alpha value may represent a minimum change needed to be made to the set of attributes to change the negative decision to a positive decision. The alpha value may then be applied to the latent representation to generate an updated latent representation, which may then be decoded into an updated set of attributes that would generate a positive decision from the automated system.

Abstract: Methods and systems are for using machine learning models to locate information in an organizational graph. A search system may use techniques described herein to determine relevant data (e.g., organizational knowledge) to retrieve from a knowledge graph for input to a machine learning model. The search system may retrieve more relevant data from the knowledge graph through the use of time data that may enable the search system to avoid outdated information. The search system may also limit the data that may be used in determining an answer to a query. By doing so, the search system may be able to answer queries more efficiently (e.g., using less computing resources, less processing power, etc.).

Abstract: Systems, methods, and computer program products for identifying trends in behavior using embedding drift. A graph neural network may receive a network graph includes a plurality of nodes, the network graph based on a plurality of transactions for a first time interval, each transaction associated with at least one account. An embedding layer of the neural network may generate, based on the network graph, a respective embedding vector for each of the nodes. The neural network may receive a second embedding vector for each of the nodes. The neural network may determine, based on the embedding vectors and the second embedding vectors, a respective drift for each node. The neural network may determine that the drift of a first node is greater than the drift of a second node, and performing a processing operation on a first account corresponding to the first node.

Abstract: Systems, methods, and computer program products to provide credit decisioning based on graph neural networks. A lending network graph of a plurality of loans may be received, each loan associated with a creditor and one account. A first node of the graph may be associated with a first creditor and the second node may be associated with a first account. A graph neural network may receive a respective message from each node connected to the first node, each message comprising an embedding vector reflecting a current state of the node. The graph neural network may update weights for the first node in a forward pass. The graph neural network may receive a respective message from each node connected to the second node, each message comprising the embedding vector reflecting the current state of the node. The graph neural network may update weights for the second node in a backward pass.

Abstract: Systems, methods, and computer program products to provide credit decisioning based on graph neural networks. A lending network graph of a plurality of loans may be received, each loan associated with a creditor and one account. A first node of the graph may be associated with a first creditor and the second node may be associated with a first account. A graph neural network may receive a respective message from each node connected to the first node, each message comprising an embedding vector reflecting a current state of the node. The graph neural network may update weights for the first node in a forward pass. The graph neural network may receive a respective message from each node connected to the second node, each message comprising the embedding vector reflecting the current state of the node. The graph neural network may update weights for the second node in a backward pass.

Abstract: Systems, methods, and computer program products to provide credit decisioning based on graph neural networks. A lending network graph of a plurality of loans may be received, each loan associated with a creditor and one account. A first node of the graph may be associated with a first creditor and the second node may be associated with a first account. A graph neural network may receive a respective message from each node connected to the first node, each message comprising an embedding vector reflecting a current state of the node. The graph neural network may update weights for the first node in a forward pass. The graph neural network may receive a respective message from each node connected to the second node, each message comprising the embedding vector reflecting the current state of the node. The graph neural network may update weights for the second node in a backward pass.

Abstract: Systems, methods, and computer program products to provide neural embeddings of transaction data. A network graph of transaction data based on a plurality of transactions may be received. The network graph of transaction data may define relationships between the transactions, each transaction associated with at least a merchant and an account. A neural network may be trained based on training data comprising a plurality of positive entity pairs and a plurality of negative entity pairs. An embedding function may then encode transaction data for a first new transaction. An embeddings layer of the neural network may determine a vector for the first new transaction based on the encoded transaction data for the first new transaction. A similarity between the vectors for the transactions may be determined. The first new transaction may be determined to be related to the second transaction based on the similarity.

Abstract: Systems, methods, and computer program products to provide neural embeddings of transaction data. A network graph of transaction data based on a plurality of transactions may be received. The network graph of transaction data may define relationships between the transactions, each transaction associated with at least a merchant and an account. A neural network may be trained based on training data comprising a plurality of positive entity pairs and a plurality of negative entity pairs. An embedding function may then encode transaction data for a first new transaction. An embeddings layer of the neural network may determine a vector for the first new transaction based on the encoded transaction data for the first new transaction. A similarity between the vectors for the transactions may be determined. The first new transaction may be determined to be related to the second transaction based on the similarity.

Abstract: Systems, methods, and computer program products to provide neural embeddings of transaction data. A network graph of transaction data based on a plurality of transactions may be received. The network graph of transaction data may define relationships between the transactions, each transaction associated with at least a merchant and an account. A neural network may be trained based on training data comprising a plurality of positive entity pairs and a plurality of negative entity pairs. An embedding function may then encode transaction data for a first new transaction. An embeddings layer of the neural network may determine a vector for the first new transaction based on the encoded transaction data for the first new transaction. A similarity between the vectors for the transactions may be determined. The first new transaction may be determined to be related to the second transaction based on the similarity.