Abstract: Methods and systems are described herein for synchronizing communication records in computer networks. For example, the methods and systems may determine whether or not a first communication relates to a second and generate a recommendation that the communications relate to a single communication. In particular, the methods and systems described herein describe synchronizing communication records in computer networks based on detecting patterns in categories of metadata. For example, the methods and systems retrieve specific types of metadata and compare this metadata between communications in order to synchronize and/or deduplicate them.

Abstract: In some implementations, an automated information transfer system may receive an indication of a location of the user device. The automated information transfer system may identify an interacting entity associated with the automated information transfer that is associated with a physical location that is within a threshold proximity of the location of the user device. The automated information transfer system may receive item-specific data associated with the automated information transfer. The automated information transfer system may identify one or more interaction terminals at the physical location associated with the interacting entity. The automated information transfer system may receive authorization information associated with the automated information transfer.

Abstract: Systems, methods, apparatuses, and computer-readable media are provided for determining individual item-level details associated with a transaction. A plurality of purchase transactions associated with different merchants may be displayed via a user interface. Responsive to a user selection of a first transaction, of the plurality of transactions, a camera may capture an image of at least a portion of a user receipt associated with the first transaction. The image of the user receipt may be analyzed using one or more optical character recognition (OCR) algorithms to convert the image of the user receipt into textual data. One or more character strings associated with line item-level details may be extracted from the textual data associated with the first transaction. Additional information associated with the line item details may be determined and the line item details and the additional information may be displayed via a user interface.

Abstract: The present disclosure describes a generative artificial intelligence-based solution for generating a narrative associated with a transaction. The generative artificial intelligence described herein acquires one or more data points associated with the transaction. Based on these data points, the generative artificial intelligence may generate one or more narratives for the transaction. The one or more narratives may be provided to a user device for a user's review and/or approval. After a narrative is approved, the narrative may be stored. If the transaction is later contested, the narrative may be provided to user to refresh their recollection about the circumstances regarding the transaction.

Abstract: Systems as described herein may classify entities based on cleansed transactions. An entity classification server may obtain transaction data indicating an entity name and an entity code in a non-standardized format. A recommended entity code in a standardized format may be determined from a remote data store. The entity classification server may generate a score indicating a likelihood that the recommended entity code correctly identifies the entity indicated in the transaction data using a machine classifier. The entity classification server may update the entity code in the transaction data with the recommended entity code based on the score exceeding a threshold value. Accordingly, a transaction summary comprising the transaction data may be generated and provided to a computing device.

Abstract: In some implementations, a credential system may create a virtual credential bound to a physical location associated with a transacting entity based on a request from a user device. The credential system may send information to a transaction terminal at the physical location bound to the virtual credential to register the virtual credential and identify a user that owns an account associated with the virtual credential. The credential system may provide, to the user device, tokenized information related to the virtual credential. The credential system may receive the tokenized information from a transaction terminal requesting authorization for the transaction. The credential system may send, to the transaction terminal requesting the authorization for the transaction, an authorization decision associated with the transaction based on whether the transaction terminal is present at the physical location bound to the virtual credential.

Abstract: Disclosed embodiments may include a method for automated creation of transaction cleansing overrides. The system may include one or more processors, and memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the system to receive a communication from a card holder via one of one or more communication channels and analyze the communication using a first machine learning model to determine an identity of the card holder, detect a mislabeled name, and detect a temporal indicator. In some embodiments, the mislabeled name and the temporal indicator are associated with a transaction. In some embodiments, the memory can be further configured to cause the system to detect card holder records and raw data associated with the transaction; generate a key based on the raw data; and alter an override list to add the key.

Abstract: Systems and methods for training machine learning models using differentiation. In some aspects, the system receives a set of triplet inputs. Each triplet input includes a resource access request, a correct reference classification, and an incorrect classification. The system initializes a first machine learning model. The system updates the first machine learning model by, for each triplet input in the set of triplet inputs, processing the resource access request using the first machine learning model first in conjunction with the correct reference classification then in conjunction with the incorrect classification to generate a set of first distances and a set of second distances, respectively. Based on the set of first distances and the set of second distances, the system computes a loss metric to update parameters for the first machine learning model. The system processes second resource access requests using the first machine learning model to generate predicted classifications.

Abstract: Systems as described herein may classify entities based on cleansed transactions. An entity classification server may obtain transaction data indicating an entity name and an entity code in a non-standardized format. A recommended entity code in a standardized format may be determined from a remote data store. The entity classification server may generate a score indicating a likelihood that the recommended entity code correctly identifies the entity indicated in the transaction data using a machine classifier. The entity classification server may update the entity code in the transaction data with the recommended entity code based on the score exceeding a threshold value. Accordingly, a transaction summary comprising the transaction data may be generated and provided to a computing device.

Abstract: In some implementations, a credential system may create a virtual credential bound to a physical location associated with a transacting entity based on a request from a user device. The credential system may send information to a transaction terminal at the physical location bound to the virtual credential to register the virtual credential and identify a user that owns an account associated with the virtual credential. The credential system may provide, to the user device, tokenized information related to the virtual credential. The credential system may receive the tokenized information from a transaction terminal requesting authorization for the transaction. The credential system may send, to the transaction terminal requesting the authorization for the transaction, an authorization decision associated with the transaction based on whether the transaction terminal is present at the physical location bound to the virtual credential.

Abstract: A method and related system for generating new rules and patterns to detect identifiers includes operations to obtain a first set of messages comprising a set of identifiers and determining a labeled set of messages associated with a target identifier of the set of identifiers based on detected matches between the target identifier and text extracted from the first set of messages with a first construct. The method further includes determining a characterizing value based on the labeled set of messages and determining whether the set of characterizing values satisfies a set of criteria. The operations further include performing a search for the target identifier in a database of messages to retrieve a set of matching messages based on a result indicating that the set of characterizing values satisfies the set of criteria. The operations further include generating a second construct based on the set of matching messages.

Abstract: Disclosed embodiments may include a method that includes receiving description data in an originating language for a user and a location associated with the user, identifying one or more names from the description data, retrieving additional data in the originating language based on the one or more names, generating enhanced description data in the originating language for the user based on the description data and the additional data, identifying a target language based on the location associated with the user, selecting a first trained neural network from a plurality of trained neural networks based the target language, providing the enhanced description data in the originating language to the first trained neural network, translating, via the first trained neural network, the enhanced description data from the originating language to the target language, and generating a graphical user interface for display that comprises the enhanced description data in the target language.

Abstract: Aspects described herein may allow for determining network membership to facilitate detecting fraudulent messages. A computing device may receive, from one or more terminals at a first location, a plurality of interactive messages during a pre-determined time period. Each interactive message may comprise personally identifiable information of a user. The computing device may store a first record and a second record that indicate interactive messages were received from a group of users in temporal proximity to each other at the first location and the second location respectively. The computing device may send a request to confirm users in the subset are members of a network and update a membership list based on a reply received from the user. If further messages are received from devices outside the membership list, an alert may be sent to alert the possibility of a fraudulent message.

Abstract: In some implementations, an automated information transfer system may receive an indication of a location of the user device. The automated information transfer system may identify an interacting entity associated with the automated information transfer that is associated with a physical location that is within a threshold proximity of the location of the user device. The automated information transfer system may receive item-specific data associated with the automated information transfer. The automated information transfer system may identify one or more interaction terminals at the physical location associated with the interacting entity. The automated information transfer system may receive authorization information associated with the automated information transfer.

Abstract: In some implementations, a data cleaning platform may determine a respective entity key for each data record in a cleansed dataset based on a combination of fields, in each data record, that contain information that uniquely identifies an entity associated with a respective data record. The data cleaning platform may generate a delta dataset based on a set of uncleansed data records related to transactions that occurred after a time when the cleansed dataset was first generated. For example, in some implementations, each uncleansed data record in the delta dataset may be associated with a corresponding entity key based on the combination of fields. The data cleaning platform may perform a data join to update the cleansed dataset to include data records related to the transactions that occurred after the time when the cleansed dataset was first generated.

Abstract: Methods and systems are described herein for synchronizing communication records in computer networks. For example, the methods and systems may determine whether or not a first communication relates to a second and generate a recommendation that the communications relate to a single communication. In particular, the methods and systems described herein describe synchronizing communication records in computer networks based on detecting patterns in categories of metadata. For example, the methods and systems retrieve specific types of metadata and compare this metadata between communications in order to synchronize and/or deduplicate them.

Abstract: Systems, methods, apparatuses, and computer-readable media are provided for determining individual item-level details associated with a transaction. A plurality of purchase transactions associated with different merchants may be displayed via a user interface. Responsive to a user selection of a first transaction, of the plurality of transactions, a camera may capture an image of at least a portion of a user receipt associated with the first transaction. The image of the user receipt may be analyzed using one or more optical character recognition (OCR) algorithms to convert the image of the user receipt into textual data. One or more character strings associated with line item-level details may be extracted from the textual data associated with the first transaction. Additional information associated with the line item details may be determined and the line item details and the additional information may be displayed via a user interface.

Abstract: Methods and systems are described herein for synchronizing communication records in computer networks. For example, the methods and systems may determine whether or not a first communication relates to a second and generate a recommendation that the communications relate to a single communication. In particular, the methods and systems described herein describe synchronizing communication records in computer networks based on detecting patterns in categories of metadata. For example, the methods and systems retrieve specific types of metadata and compare this metadata between communications in order to synchronize and/or deduplicate them.

Abstract: In some implementations, a device may obtain first location data associated with one or more exchanges, where the first location data is associated with a first level of granularity. The device may determine second location data associated with the one or more exchanges based on records associated with the one or more exchanges, where the second location data is associated with a second level of granularity that is higher than the first level of granularity. The device may detect an authentication event associated with an access attempt to the account. The device may provide, based on detecting the authentication event, one or more authentication queries that are based on the second location data. The device may authenticate the access attempt to the account based on one or more responses to the one or more authentication queries.

Abstract: In some implementations, a credential system may create a virtual credential bound to a physical location associated with a transacting entity based on a request from a user device. The credential system may send information to a transaction terminal at the physical location bound to the virtual credential to register the virtual credential and identify a user that owns an account associated with the virtual credential. The credential system may provide, to the user device, tokenized information related to the virtual credential. The credential system may receive the tokenized information from a transaction terminal requesting authorization for the transaction. The credential system may send, to the transaction terminal requesting the authorization for the transaction, an authorization decision associated with the transaction based on whether the transaction terminal is present at the physical location bound to the virtual credential.