Abstract: Methods for generating transaction profile tags from profile transaction activity may include receiving a transaction profile including recorded transactions, associating at least one transaction label with each of the transactions, the labels associated with transaction types, generating a set of profile features based on the recorded transactions from the transaction profile, encoding the set of profile features with a macro-encoder into a first-reduced set, clustering the first-reduced set into at least two subsets, each associated with a macro-profile tag, and tagging the transaction profile with one of the macro-profile tags. Methods may also include encoding the set of profile features with a micro-encoder selected based on the tagged macro-profile tag, clustering the second-reduced set into a plurality of subsets associated with account profile types, respectively, and tagging the transaction profile with a tag associated with the account profile type.

Abstract: Provided are methods for determining a dominant account profile of an account. The method may include receiving transaction data associated with a plurality of payment transactions conducted within a predetermined time interval of activation of an account involved in the plurality of payment transactions, generating a dominant account profile classification model, determining a plurality of prediction scores for the account based on the dominant account profile classification model and the transaction data, where determining the plurality of prediction scores includes determining, for the user, a prediction score for each dominant account profile, where a prediction score includes a prediction of whether the user will conduct a threshold value of payment transactions using the account in one or more payment transaction categories of a plurality of payment transaction categories, and communicating data associated with the plurality of prediction scores. Systems and computer program products are also disclosed.

Abstract: Provided is a computer-implemented method for determining a dominant account profile of an account. The method may include receiving transaction data associated with a plurality of payment transactions conducted within a predetermined time interval of activation of an account involved in the plurality of payment transactions, generating a dominant account profile classification model, determining a plurality of prediction scores for the account based on the dominant account profile classification model and the transaction data, where determining the plurality of prediction scores includes determining, for the user, a prediction score for each dominant account profile, where a prediction score includes a prediction of whether the user will conduct a threshold value of payment transactions using the account in one or more payment transaction categories of a plurality of payment transaction categories, and communicating data associated with the plurality of prediction scores.

Abstract: A method, system, and computer program product for determining customer migration: obtain first feature data for a plurality of users associated with a first time period; segment the plurality of users into a plurality of groups based on the first feature data; identify a center point of each group based on the feature data; obtain second feature data for one or more users of the plurality of users associated with a second time period; determine a distance between the one or more users and each center point of each group based on the second feature data; and assign the one or more users to a group of the plurality of groups based on the distance between the one or more users and each center point of each group.

Abstract: Merchant transaction data for a group of merchants, category transaction data for the group of merchants, and merchant location data for the group of merchants may be obtained for a first time period and a second time period. The merchant transaction data may include a first set of parameters. The category transaction data may include a second set of parameters, and the location data may include a third set of parameters. Additional data during the first time period and the second time period may also be obtained. The additional data may include a fourth set of parameters. The merchant transaction data, the category transaction data, the merchant location data, and the additional data may be analyzed using a machine learning program to generate a set of key parameters to predict merchant performance. A first list of merchants that are predicted to grow may be generated using the key parameters.

Abstract: Methods for generating transaction profile tags from profile transaction activity may include receiving a transaction profile including recorded transactions, associating at least one transaction label with each of the transactions, the labels associated with transaction types, generating a set of profile features based on the recorded transactions from the transaction profile, encoding the set of profile features with a macro-encoder into a first-reduced set, clustering the first-reduced set into at least two subsets, each associated with a macro-profile tag, and tagging the transaction profile with one of the macro-profile tags. Methods may also include encoding the set of profile features with a micro-encoder selected based on the tagged macro-profile tag, clustering the second-reduced set into a plurality of subsets associated with account profile types, respectively, and tagging the transaction profile with a tag associated with the account profile type.

Abstract: Methods for generating transaction profile tags from profile transaction activity may include receiving a transaction profile including recorded transactions, associating at least one transaction label with each of the transactions, the labels associated with transaction types, generating a set of profile features based on the recorded transactions from the transaction profile, encoding the set of profile features with a macro-encoder into a first-reduced set, clustering the first-reduced set into at least two subsets, each associated with a macro-profile tag, and tagging the transaction profile with one of the macro-profile tags. Methods may also include encoding the set of profile features with a micro-encoder selected based on the tagged macro-profile tag, clustering the second-reduced set into a plurality of subsets associated with account profile types, respectively, and tagging the transaction profile with a tag associated with the account profile type.

Abstract: A method, system, and computer program product for determining customer migration obtain first feature data for a plurality of users associated with a first time period; segment the plurality of users into a plurality of groups based on the first feature data; identify a center point of each group based on the feature data; obtain second feature data for one or more users of the plurality of users associated with a second time period; determine a distance between the one or more users and each center point of each group based on the second feature data; and assign the one or more users to a group of the plurality of groups based on the distance between the one or more users and each center point of each group.

Abstract: Provided is a computer-implemented method for determining a dominant account profile of an account. The method may include receiving transaction data associated with a plurality of payment transactions conducted within a predetermined time interval of activation of an account involved in the plurality of payment transactions, generating a dominant account profile classification model, determining a plurality of prediction scores for the account based on the dominant account profile classification model and the transaction data, where determining the plurality of prediction scores includes determining, for the user, a prediction score for each dominant account profile, where a prediction score includes a prediction of whether the user will conduct a threshold value of payment transactions using the account in one or more payment transaction categories of a plurality of payment transaction categories, and communicating data associated with the plurality of prediction scores.

Abstract: Merchant transaction data for a group of merchants, category transaction data for the group of merchants, and merchant location data for the group of merchants may be obtained for a first time period and a second time period. The merchant transaction data may include a first set of parameters. The category transaction data may include a second set of parameters, and the location data may include a third set of parameters. Additional data during the first time period and the second time period may also be obtained. The additional data may include a fourth set of parameters. The merchant transaction data, the category transaction data, the merchant location data, and the additional data may be analyzed using a machine learning program to generate a set of key parameters to predict merchant performance. A first list of merchants that are predicted to grow may be generated using the key parameters.

Abstract: Methods for generating transaction profile tags from profile transaction activity may include receiving a transaction profile including recorded transactions, associating at least one transaction label with each of the transactions, the labels associated with transaction types, generating a set of profile features based on the recorded transactions from the transaction profile, encoding the set of profile features with a macro-encoder into a first-reduced set, clustering the first-reduced set into at least two subsets, each associated with a macro-profile tag, and tagging the transaction profile with one of the macro-profile tags. Methods may also include encoding the set of profile features with a micro-encoder selected based on the tagged macro-profile tag, clustering the second-reduced set into a plurality of subsets associated with account profile types, respectively, and tagging the transaction profile with a tag associated with the account profile type.