Abstract: First data indicative of a first plurality of transactions by a user may be processed to generate first behavioral information describing the user. The first behavioral information may be displayed by an interactive user interface. A user input made in response to the first behavioral information may be received and analyzed to generate user preference information indicating a relationship between the first user input and the first behavioral information. Second data indicative of a second plurality of transactions by the user may be received and processed with the user preference information to generate second behavioral information describing the user. The second behavioral information may be displayed by the interactive user interface differently from the first behavioral information by the interactive user interface as a result of the processing of the second data and the user preference information together.

Abstract: Provided, in an aspect, is a method for improved visualization of transaction data from a financial services computer network. The method includes receiving, at a computing device, a plurality of experience sets; presenting, on a display of the computing device, a graphical user interface (GUI); and updating the GUI in response to receiving a revision to the plurality of experience sets. Each experience set contains one or more transactions that relate to each other. The GUI includes a scrollable list having at least a portion of the experience set name for experience sets within a selected time period; and a calendar for the time period showing, for each day with at least one experience, a graphical element indicative of a total of all experience set amounts in that day.

Abstract: First data indicative of a first plurality of transactions by a user may be processed to generate first behavioral information describing the user. The first behavioral information may be displayed by an interactive user interface. A user input made in response to the first behavioral information may be received and analyzed to generate user preference information indicating a relationship between the first user input and the first behavioral information. Second data indicative of a second plurality of transactions by the user may be received and processed with the user preference information to generate second behavioral information describing the user. The second behavioral information may be displayed by the interactive user interface differently from the first behavioral information by the interactive user interface as a result of the processing of the second data and the user preference information together.

Abstract: Provided, in an aspect, is a system for managing transactions from a financial services computer network. The system has a scalable architecture, and includes a database, one or more processors, a plurality of experience matchers, and a transaction hub. Each experience matcher is associated with a different experience set type, and can receive a transaction list and return an identified experience set. The transaction hub can communicate with multiple experience matchers, and can receive experience sets from the matchers after sending them a list of transactions.

Abstract: First data indicative of a first plurality of transactions by a user may be processed to generate first behavioral information describing the user. The first behavioral information may be displayed by an interactive user interface. A user input made in response to the first behavioral information may be received and analyzed to generate user preference information indicating a relationship between the first user input and the first behavioral information. Second data indicative of a second plurality of transactions by the user may be received and processed with the user preference information to generate second behavioral information describing the user. The second behavioral information may be displayed by the interactive user interface differently from the first behavioral information by the interactive user interface as a result of the processing of the second data and the user preference information together.

Abstract: Provided, in an aspect, is a system for managing transactions from a financial services computer network. The system has a scalable architecture, and includes a database, one or more processors, a plurality of experience matchers, and a transaction hub. Each experience matcher is associated with a different experience set type, and can receive a transaction list and return an identified experience set. The transaction hub can communicate with multiple experience matchers, and can receive experience sets from the matchers after sending them a list of transactions.

Abstract: First data indicative of a first plurality of transactions by a user may be processed to generate first behavioral information describing the user. The first behavioral information may be displayed by an interactive user interface. A user input made in response to the first behavioral information may be received and analyzed to generate user preference information indicating a relationship between the first user input and the first behavioral information. Second data indicative of a second plurality of transactions by the user may be received and processed with the user preference information to generate second behavioral information describing the user. The second behavioral information may be displayed by the interactive user interface differently from the first behavioral information by the interactive user interface as a result of the processing of the second data and the user preference information together.

Abstract: Provided, in an aspect, is a method for improved management of transaction data from a financial services computer network. The method includes receiving details for a first purchase, detecting that the first purchase is a trigger purchase, obtaining secondary details for the first purchase, receiving details for a later-made second purchase and additional purchases made between the first purchase and second purchase, and determining that the first purchase and the second purchase belong to the same experience set and that the additional intervening purchases do not belong to the same experience set as the first purchase and the second purchase.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for providing consistent processing in a machine learning system are disclosed. A real-time processing request may be received and processed by both a preferred machine learning model and a fallback machine learning model. Processing for the preferred machine learning model may include obtaining additional information. A determination may be made regarding whether the processing of the real-time request by the preferred machine learning model has completed as of an expiration of an acceptable latency period. If the preferred model has not completed as of the expiration of an acceptable latency period, the response to the real-time request may be generated from the fallback model output. If the preferred model has completed prior to or by the expiration of the acceptable latency period, the response to the request may be generated from the preferred model output.

Abstract: First data indicative of a first plurality of transactions by a user may be processed to generate first behavioral information describing the user. The first behavioral information may be displayed by an interactive user interface. A user input made in response to the first behavioral information may be received and analyzed to generate user preference information indicating a relationship between the first user input and the first behavioral information. Second data indicative of a second plurality of transactions by the user may be received and processed with the user preference information to generate second behavioral information describing the user. The second behavioral information may be displayed by the interactive user interface differently from the first behavioral information by the interactive user interface as a result of the processing of the second data and the user preference information together.

Abstract: Provided, in an aspect, is a method for improved visualization of transaction data from a financial services computer network. The method includes receiving, at a computing device, a plurality of experience sets; presenting, on a display of the computing device, a graphical user interface (GUI); and updating the GUI in response to receiving a revision to the plurality of experience sets. Each experience set contains one or more transactions that relate to each other. The GUI includes a scrollable list having at least a portion of the experience set name for experience sets within a selected time period; and a calendar for the time period showing, for each day with at least one experience, a graphical element indicative of a total of all experience set amounts in that day.

Abstract: Provided, in an aspect, is a method for improved visualization of transaction data from a financial services computer network. The method includes receiving, at a computing device, a plurality of experience sets; presenting, on a display of the computing device, a graphical user interface (GUI); and updating the GUI in response to receiving a revision to the plurality of experience sets. Each experience set contains one or more transactions that relate to each other. The GUI includes a scrollable list having at least a portion of the experience set name for experience sets within a selected time period; and a calendar for the time period showing, for each day with at least one experience, a graphical element indicative of a total of all experience set amounts in that day.

Abstract: First data indicative of a first plurality of transactions by a user may be processed to generate first behavioral information describing the user. The first behavioral information may be displayed by an interactive user interface. A user input made in response to the first behavioral information may be received and analyzed to generate user preference information indicating a relationship between the first user input and the first behavioral information. Second data indicative of a second plurality of transactions by the user may be received and processed with the user preference information to generate second behavioral information describing the user. The second behavioral information may be displayed by the interactive user interface differently from the first behavioral information by the interactive user interface as a result of the processing of the second data and the user preference information together.

Abstract: Provided, in an aspect, is a method for improved management of transaction data from a financial services computer network. The method includes receiving details for a first purchase, detecting that the first purchase is a trigger purchase, obtaining secondary details for the first purchase, receiving details for a later-made second purchase and additional purchases made between the first purchase and second purchase, and determining that the first purchase and the second purchase belong to the same experience set and that the additional intervening purchases do not belong to the same experience set as the first purchase and the second purchase.

Abstract: Provided, in an aspect, is a method for improved visualization of transaction data from a financial services computer network. The method includes receiving, at a computing device, a plurality of experience sets; presenting, on a display of the computing device, a graphical user interface (GUI); and updating the GUI in response to receiving a revision to the plurality of experience sets. Each experience set contains one or more transactions that relate to each other. The GUI includes a scrollable list having at least a portion of the experience set name for experience sets within a selected time period; and a calendar for the time period showing, for each day with at least one experience, a graphical element indicative of a total of all experience set amounts in that day.

Abstract: First data indicative of a first plurality of transactions by a user may be processed to generate first behavioral information describing the user. The first behavioral information may be displayed by an interactive user interface. A user input made in response to the first behavioral information may be received and analyzed to generate user preference information indicating a relationship between the first user input and the first behavioral information. Second data indicative of a second plurality of transactions by the user may be received and processed with the user preference information to generate second behavioral information describing the user. The second behavioral information may be displayed by the interactive user interface differently from the first behavioral information by the interactive user interface as a result of the processing of the second data and the user preference information together.

Abstract: Provided, in an aspect, is a system for managing transactions from a financial services computer network. The system has a scalable architecture, and includes a database, one or more processors, a plurality of experience matchers, and a transaction hub. Each experience matcher is associated with a different experience set type, and can receive a transaction list and return an identified experience set. The transaction hub can communicate with multiple experience matchers, and can receive experience sets from the matchers after sending them a list of transactions.

Abstract: System and methods for determining network threats are disclosed. For each entity operating in a network being monitored for network security, an example method obtains an observed metric value for each metric that characterizes actions performed by the entity. Each observed metric value may be input into a machine learning model that is specific to the metric in order to determine an anomaly score for the observed metric value that represents how anomalous the observed metric value is relative to an expected metric value for the metric. A threat score may then be determined for each entity from the anomaly scores for each metric. A security threat presentation that identifies one or more high-scoring entities according to the threat scores may be generated and provided for display on a user device.

Abstract: System and methods for determining network threats are disclosed. For each entity operating in a network being monitored for network security, an example method obtains an observed metric value for each metric that characterizes actions performed by the entity. Each observed metric value may be input into a machine learning model that is specific to the metric in order to determine an anomaly score for the observed metric value that represents how anomalous the observed metric value is relative to an expected metric value for the metric. A threat score may then be determined for each entity from the anomaly scores for each metric. A security threat presentation that identifies one or more high-scoring entities according to the threat scores may be generated and provided for display on a user device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for providing consistent processing in a machine learning system are disclosed. A real-time processing request may be received and processed by both a preferred machine learning model and a fallback machine learning model. Processing for the preferred machine learning model may include obtaining additional information. A determination may be made regarding whether the processing of the real-time request by the preferred machine learning model has completed as of an expiration of an acceptable latency period. If the preferred model has not completed as of the expiration of an acceptable latency period, the response to the real-time request may be generated from the fallback model output. If the preferred model has completed prior to or by the expiration of the acceptable latency period, the response to the request may be generated from the preferred model output.