Abstract: Methods and systems for determining attrition at a merchant are disclosed. The method performed by the server system includes accessing information related to a subset of cardholders from a database. The method includes generating a set of features for each cardholder in the subset of cardholders based, at least in part, on transaction attributes associated with each transaction performed by each cardholder. The method includes generating an opt-out feature for each cardholder based on a historical transaction dataset. Herein, the opt-out feature indicates whether an individual cardholder has requested to cancel ongoing recurrent payments with the merchant. The method also includes generating, by a Machine Learning model, an attrition score for each cardholder based, at least in part, on the corresponding set of features, and the corresponding opt-out feature of each cardholder. The attrition score indicates a probability of each cardholder refraining from engaging in future transactions with the merchant.

Abstract: Methods and server systems for refining a training dataset for training a Machine Learning (ML) model are described herein. Method performed by a server system includes accessing multiple data segments, each data segment including a subset of training samples of training dataset. Method includes computing, by a first prediction model, gradient scores for each data segment indicating a concept drift-based relevancy of a particular data segment among multiple data segments. Method includes filtering multiple data segments to obtain filtered data segments based on the gradient scores and gradient thresholds. Method includes determining, by a second prediction model, a top-ranked batch set based on multiple data segments, a test dataset, and a refining condition. Method includes generating a refined training dataset, including a set of relevant training batches based on the filtered data segments, and the top-ranked batch set to train the ML model for obtaining a trained ML model.

Abstract: Methods and systems for training a Machine Learning (ML) model with graph structure information are disclosed. The method performed by a server system includes accessing for each node in a graph, node features, class label, and attention score from a database, determining difficulty metric and generating sequence of node batches for training the student ML model. Each node batch includes a subset of nodes in a predefined difficulty metric range associated with each node batch. Method includes training the student ML model based on performing, iteratively, first set of operations including: selecting node batch; generating node embeddings; determining positive embedding pairs and negative embedding pairs based on the attention score; computing, by an attention-aided contrastive loss function, losses including at least an attention-aided contrastive loss; and optimizing the student model parameters based on the losses. For a subsequent iteration, a subsequent node batch is selected from the sequence.

Abstract: A method is disclosed. The method includes receiving interaction data related to a plurality of interactions in a time period, determining a multiple variable regression formula, and then determining a coefficient of determination associated with the multiple variable regression formula and the interaction data. The method further includes determining if the coefficient of determination satisfies a threshold or is maximized. If the coefficient of determination does not satisfy the threshold or is not maximized, then adjusting the slope coefficients. If the coefficient of determination does satisfy the threshold or is maximized, then using the multiple variable regression formula to determine risk associated with future interactions.

Abstract: Methods and systems for determining risk associated with tokenization of payment cards are disclosed. The method performed by a server system includes receiving a tokenization request message requesting for a tokenization of a payment card of a cardholder for a particular merchant from a token requester. The tokenization request message includes card credential information. Further, the method includes accessing a cardholder-token feature set corresponding to the cardholder and a token requester feature set corresponding to the token requester from a database associated with the server system based, at least in part, on the card credential information. Furthermore, the method includes generating, by a Machine Learning (ML) model associated with the server system, a risk score indicating a risk corresponding to a transaction associated with the tokenization request message based, at least in part, on the cardholder-token feature set, the token requester feature set, and scoring criteria.

Abstract: Methods and systems for managing default risk associated with transit transactions are disclosed. The method performed by server system includes receiving a payment authentication request associated with a transit transaction performed by a payment card and identifying a card status of the payment card, the card status indicating whether the payment card is associated with a risky label or non-risky label. Upon identifying that the payment card is associated with risky label, accessing a pre-auth feature set. Method includes computing, by a pre-auth machine learning model, a pre-auth score based on the pre-auth feature set. Method includes determining a pre-auth amount for a predefined time period based on comparing the pre-auth score with a plurality of predefined pre-auth thresholds and transmitting a risk indication message including at least the card status and the pre-auth amount to the merchant.

Abstract: A method is disclosed. The method includes receiving claim requests from a plurality of service provider computers associated with a plurality of service providers for fulfillment by a plurality of payors. Each claim request includes service provider information, payor information, and beneficiary information. The method also includes validating the claim requests, and determining for each service provider of the plurality of service providers, a net amount to be transferred to the service provider. The net amount is associated with a plurality of claim requests made by the service provider for different beneficiaries serviced by the service provider. The different beneficiaries may be associated with different payors. The method further includes facilitating for each of the service providers, a single funds transfer in the net amount to be transferred to the service provider.

Abstract: Systems, methods, and computer program products are provided for on-vehicle electronic fee collection. An example system includes at least one processor configured to receive event data from a vehicle operated by a user, the event data including a digital signature based on sensor data generated by at least one sensor of the vehicle. The at least one processor may be configured to determine a merchant system from a plurality of merchant systems based on the payment event and determine a payment event based on the event data. The at least one processor may be configured to generate transaction data based on the payment event and the merchant system and transmit a payment request message including the transaction data to the vehicle. The at least one processor may be configured to process a payment transaction based on the transaction data in response to receiving a payment confirmation message from the vehicle.

Abstract: A system, method, and computer program product are provided for consent management. A method may include receiving a first data request for user data associated with a user, the user data stored in a user data database; communicating a consent request to the requester system; receiving a consent response from the requester system; storing consent data associated with the consent response for the user data requested in the first data request in an immutable ledger; receiving a consent verification request from the user data database, the consent verification request based on a second data request for the user data from the requester system to the user data database; verifying the consent verification request based on the consent data; and communicating a consent verification response to the user data database, the consent verification response indicating consent from the user to share the user data with the requester system.

Abstract: A method is disclosed. The method includes receiving interaction data related to a plurality of interactions in a time period, determining a multiple variable regression formula, and then determining a coefficient of determination associated with the multiple variable regression formula and the interaction data. The method further includes determining if the coefficient of determination satisfies a threshold or is maximized. If the coefficient of determination does not satisfy the threshold or is not maximized, then adjusting the slope coefficients. If the coefficient of determination does satisfy the threshold or is maximized, then using the multiple variable regression formula to determine risk associated with future interactions.

Abstract: A system, method, and computer program product are provided for consent management. A method may include receiving a first data request for user data associated with a user, the user data stored in a user data database; communicating a consent request to the requester system; receiving a consent response from the requester system; storing consent data associated with the consent response for the user data requested in the first data request in an immutable ledger; receiving a consent verification request from the user data database, the consent verification request based on a second data request for the user data from the requester system to the user data database; verifying the consent verification request based on the consent data; and communicating a consent verification response to the user data database, the consent verification response indicating consent from the user to share the user data with the requester system.

Abstract: Systems, methods, and computer program products are provided for privacy-preserved data services using generative AI abstraction. The system includes at least one processor configured to generate a user profile based on identification data of a user by inputting the identification data to a generative machine learning model, generate abstracted datasets based on outputs of the generative machine learning model, and associate abstracted datasets with the user profile. The at least one processor is further configured to receive a request message from a third-party computing device comprising a query and a token associated with the user profile, determine the user profile based on the token, and generate outputs based on the query and the abstracted datasets associated with the user profile. The at least one processor is further configured to communicate a response message to the third-party computing device based on the outputs.

Abstract: Methods and server systems for mitigating negative transfer in Multi-Task Learning (MTL) are described herein. Method performed by server system includes accessing training dataset and training multi-task machine learning (MTML) model based on performing operations. The operations includes initializing MTML model based on model parameters. Then, computing task affinity metric for each task of a set of tasks based on determining an affinity between each task and one or more tasks. Then, computing task-specific activation probability for each task based on task affinity metric corresponding to each task. Then, activating subset of tasks when task-specific activation probability corresponding to each individual task from the subset of tasks is lower than predefined threshold. Further, processing, via MTML model, training dataset by performing subset of tasks to compute outputs. Furthermore, generating task-specific losses for subset of tasks based on outputs and training dataset.

Abstract: Methods and server systems for generating task-agnostic representations for nodes in bipartite graph are described herein. Method performed by server system includes accessing bipartite graph including first set of nodes and second set of nodes. Herein, set of edges exist between first and second set of nodes. Method includes performing for each node of first and second set of nodes: identifying a natural neighbor node, the natural neighbor node being a two-hop neighbor node from the each node, Then, generating temporary representation for one-hop neighbor node based on set of features corresponding to the one-hop neighbor node Then, generating temporary neighbor node based on temporary representation for the one-hop neighbor node. Then, generating augmented neighborhood based on the natural node and the temporary neighbor node, and then determining via machine learning model, task-agnostic representation for the each node based on augmented neighborhood.

Abstract: A method includes: controlling a prefunded account of an issuer system by a transaction processing system; receiving first transaction requests associated with first transactions initiated by first payment devices issued by the issuer system; for each first transaction: determining that the issuer system issued a corresponding first payment device; determining an accumulated authorization amount; determining that the accumulated authorization amount does not satisfy a threshold based on the prefunded amount; and generating and communicating an authorization request associated with the corresponding first transaction to the issuer system; receiving a second transaction request associated with a second transaction initiated by a second payment device issued by the issuer system; in response to receiving the second transaction request, determining that the issuer system issued the second payment device; determining an updated accumulated authorization amount; determining that the updated accumulated authorizatio

Abstract: Methods and systems for training artificial intelligence (AI)-based models using limited labeled data are disclosed. The method performed by a server system includes accessing a tabular dataset including tabular data that further labeled data and unlabeled data. Method includes generating labeled features including labeled numerical features and labeled categorical features based on the labeled data and generating unlabeled features including unlabeled numerical features and unlabeled categorical features based on the unlabeled data. Method includes determining, via a first transformer model, a contextual numerical embeddings based on the labeled numerical features and the unlabeled numerical features. Method includes determining, via a second transformer model, a contextual categorical embeddings based on the labeled categorical features and the unlabeled categorical features.

Abstract: A system, method, and computer program product are provided for consent management. A method may include receiving a first data request for user data associated with a user, the user data stored in a user data database; communicating a consent request to the requester system; receiving a consent response from the requester system; storing consent data associated with the consent response for the user data requested in the first data request in an immutable ledger; receiving a consent verification request from the user data database, the consent verification request based on a second data request for the user data from the requester system to the user data database; verifying the consent verification request based on the consent data; and communicating a consent verification response to the user data database, the consent verification response indicating consent from the user to share the user data with the requester system.

Abstract: Embodiments relate to a composition comprising nanohydroxyapatite (NHAP) in an amount about 0.5 wt. % to about 50 wt. % of the composition having a particle size in a range of about 20-100 nm, an abrasive, a sweetener, and a natural oil, wherein the composition does not contain glycerin and fluoride, wherein the composition is alkaline and a dental product, and wherein the natural oil is a plant product.

Abstract: A system, method, and computer program product are provided for consent management. A method may include receiving a first data request for user data associated with a user, the user data stored in a user data database; communicating a consent request to the requester system; receiving a consent response from the requester system; storing consent data associated with the consent response for the user data requested in the first data request in an immutable ledger; receiving a consent verification request from the user data database, the consent verification request based on a second data request for the user data from the requester system to the user data database; verifying the consent verification request based on the consent data; and communicating a consent verification response to the user data database, the consent verification response indicating consent from the user to share the user data with the requester system.

Abstract: Embodiments relate to a composition comprising nanohydroxyapatite (NHAP) in an amount about 0.5 wt. % to about 50 wt. % of the composition having a particle size in a range of about 20-100 nm, an abrasive, a sweetener, and a natural oil, wherein the composition does not contain glycerin and fluoride, wherein the composition is alkaline and a dental product, and wherein the natural oil is a plant product.