Abstract: Systems and methods for generating enhanced user interfaces are disclosed. A set of candidate items responsive to a request for an enhanced interface is generated. The set of candidate items is responsive to a query or an anchor item. A composite candidate score for each candidate item is generated by a pick item scoring engine based on one or more historical interactions. A set of top-k items is selected from the set of candidate items and at least one pick item is selected from the set of top-k items. At least one enhancement interface element is selected for display in conjunction with the at least one pick item and a response to the request for the enhanced interface is transmitted that causes a receiving device to generate a user interface including the at least one pick item displayed in conjunction with the at least one enhancement interface element.

Abstract: Systems and methods for identifying substitute elements for computer-implemented processes are disclosed. A substitution request identifying an anchor element is received. A set of candidate substitution elements is generated by a trained candidate selection model configured to receive the anchor element, a feature set, and a set of catalog elements. The set of candidate substitution elements is ranked by a trained ranking model configured to receive the anchor element, the feature set, and the set of candidate substitution elements. At least one substitution element is selected from the set of candidate substitution elements and feedback data representative of the suitability of the selected at least one substitution element with respect to the anchor element is received. At least one of the trained candidate selection model or the trained ranking model is updated by applying an iterative training process incorporating at least a portion of the feedback data.

Abstract: Disclosed herein are method, system, and computer product embodiments for generating a textual summary of a data set based on traversing a decision tree according to sequence and rank numbers related to a query. Subsets of the data set may receive a rank number indicating the relevancy of the subset of data to the query. In response to traversing the desicion tree, a textual summary representative of the data set and subsets of data may be generated and displayed. The textual summary may also include a course of action recommendation based on the culmination of the data set and relevant data subsets.

Abstract: A system and method for generating product analytics insights for machine learning platforms is disclosed. The system and method can receive a log file including data derived while executing a software program. Software packages and the package sub-modules logged in the log file may be categorized into a plurality of package categories. A notebook in which the software code is written, and identified in the log file, may be categorized into a notebook category. A consumable insight may be generated based on: the categorized software packages and package sub-modules, and the categorized notebook. A natural language summary may be generated describing the consumable insight. The natural language summary may be transmitted for display on a graphical user interface (GUI) in response to a user query.

Abstract: Systems and methods for dynamically disaggregating product variants in online search are disclosed. In some embodiments, a disclosed method includes: obtaining, from a computing device, a search request identifying a query and seeking N items to be displayed on a search result page of a website to a user, wherein N is a positive integer; determining, dynamically based on the query and N, an integer M; searching, based on the query, a database to identify M items associated with the website, wherein the M items comprise at least one subset of items that include at least one variant of a product; generating, from the M items, a ranked list of N items; and transmitting, to the computing device, the ranked list of N items in response to the search request.

Abstract: Systems and methods for generating an interface including variant item elements are disclosed. A request for an interface including a search query is received from a first device and a set of candidate items is generated by a first level search model based on the search query. The first level search model generates a baseline value for each item variant in an item catalog including a weighted combination of a relevance label value and an engagement label value. The set of candidate items is selected based on the baseline value. A set of search results is generated by a second level search model based on the set of candidate items. An interface including interface elements representative of one or more item variants in the set of search results is generated and transmitted to the first device.

Abstract: At least some embodiments are directed to a system that receives from an online portal loaded in a computing device, a user request to instantiate a server cluster in a hybrid computer network. The system authenticates and redirects the user request to a selected computer network configured in the hybrid computer network. The system instantiates the server cluster in the selected computer network causing the server cluster to initiate a microservice agent during bootup. The system sends a command to the server cluster to initiate the execution of a process and receives from the microservice agent event data associated with the process. The system inputs the event data into a trained machine learning model to determine a first execution state of the process and sends a command to change the first execution state of the process to a second execution state.

Abstract: At least some embodiments are directed to an insights inference system that produces multiple insights associated with an entity. The insights inference system generates a decision tree machine learning model, assigning a first insight to a parent node of a decision tree machine learning model and assigning at least one second insight to child nodes of the decision tree machine learning model. Each child node is associated with a sequence number and a rank number. The sequence number and the rank number are indicative of a significance associated with the at least one second insight. The insight inference system responds to queries by traversing the decision tree machine learning model to compute at least one response insight based on the sequence number and the rank number associated with each child node and outputs the at least one response insight to a client terminal.

Abstract: Disclosed are various embodiments for extracting transaction and user data from financial documents and formatting the data into a structured format to facilitate a real-time analysis of the extracted data. A user may submit an unstructured formatted financial document with a credit rating request, underwriting request, and/or other type of financial risk assessment request. Text components and a table component are identified according to a structural representation of the document. The text components are analyzed to identify and extract ownership data associated with the user that can be used to verify ownership of the provided document by the submitting user. The transaction data is identified and extracted in a structured format based at least in part on a table header location and detected column boundaries. The extracted transaction data is validated to ensure an accurate extraction of the transaction data.

Abstract: Embodiments of the present disclosure disclose methods and systems for generating operational alarms for a plurality of clients, the operational alarms being generated by a business performance system, each client being associated with a plurality of Key Performance Indicators (KPIs). An aggregate rank for each client based on ranks of each KPI is generated. For each client: the aggregate rank of the client over one or more time periods is monitored. If the aggregate rank deteriorates over the one or more time periods, a severity indicator is determined based on change of value of each KPI and change of rank of each KPI for the client over the one or more time periods. An operational alarm based on value of the severity indicator is determined. The operational alarm is displayed on a user interface, wherein the operational alarm displays one or more KPIs with highest severity values.

Abstract: At least some embodiments are directed to a system that receives from an online portal loaded in a computing device, a user request to instantiate a server cluster in a hybrid computer network. The system authenticates and redirects the user request via a proxy service to a selected computer network configured in the hybrid computer network. The system instantiates the server cluster in the selected computer network causing the server cluster to initiate a microservice agent during bootup. The system sends a command to the server cluster to initiate the execution of a process and receives from the microservice agent event data associated with the process. The system inputs the event data into a trained machine learning model to determine a first execution state of the process and sends a command to change the first execution state of the process to a second execution state.

Abstract: A technique for caching evidence for answering questions in a cache memory of a data processing system (that is configured to answer questions) includes receiving a first question. The first question is analyzed to identify a first set of characteristics of the first question. A first set of evidence for answering the first question is loaded into the cache memory. A second question is received. The second question is analyzed to identify a second set of characteristics of the second question. A portion of the first set of evidence, whose expected usage in answering the second question is below a determined threshold, is unloaded from the cache memory.

Abstract: A technique for caching evidence for answering questions in a cache memory of a data processing system (that is configured to answer questions) includes receiving a first question. The first question is analyzed to identify a first set of characteristics of the first question. A first set of evidence for answering the first question is loaded into the cache memory. A second question is received. The second question is analyzed to identify a second set of characteristics of the second question. A portion of the first set of evidence, whose expected usage in answering the second question is below a determined threshold, is unloaded from the cache memory.

Abstract: A method, system and computer program product for selecting virtual machines to be migrated to a public cloud. The current resource usage for virtual machine instances running in the private cloud is determined. Furthermore, any scaling policies attached to the virtual machine instances running in the private cloud are obtained. Additional resource usages for any of the virtual machine instances with a scaling policy are computed for when these virtual machine instances are scaled out. A cost of running a virtual machine instance in the public cloud is then determined using its current resource usage as well as any additional resource usage if a scaling policy is attached to the virtual machine instance based on the cost for running virtual machine instances in a public cloud. If the cost is less than a threshold cost, then the virtual machine instance is selected to be migrated to the public cloud.

Abstract: A computer-implemented method for deploying a plurality of data conversion flow between a first application in a first system to a second application in a second system, without restarting the plurality of data conversation flow, is provided. The computer-implemented method may further include providing a plurality of modifiable data conversation that identifies a plurality of input parameters, a plurality of data formats, a plurality of data description, a plurality of conversation routines, a plurality of paths of the conversion routines, and a plurality of output information that determines routes of converted data for the first application. The computer-implemented method may further include converting the plurality of modifiable data conversion to form a data input from the first application to the second application.

Abstract: A management system receives inputs over a period of time from outputs of one or more sensors placed within a proximity to a service area, the one or more sensors for detecting at least one of at least one weight and at least one sound. The management system dynamically estimating, based on a rate of a percentage of change of the at least one weight over the period of time and types of sounds of the at least one sound for the service area, one or more wait times until a completion of use of the service area. The management system dynamically generating one or more wait time estimates in real time for the service area based on the one or more wait times and a current number of users waiting in a queue for the service area.

Abstract: According to one aspect of the present disclosure a method and technique for dynamic system level agreement provisioning is disclosed. The method includes: identifying, by a data processing system of a computing environment service provider, service level criteria for a customer of computing services; determining characteristics of the computing environment; identifying a time period for providing the computing services; evaluating one or more utility functions defining service level variables; and automatically determining, by the data processing system, a service level agreement (SLA) provision for the customer based on the one or more utility functions.

Abstract: According to one aspect of the present disclosure a system and technique for dynamic system level agreement provisioning includes: a computing environment configured with allocatable computing resources; and a host having a processor unit operable to execute a service level agreement (SLA) module. The SLA module is configured to: identify service level criteria for a customer of computing services of the computing environment; determine characteristics of the computing environment; identify a time period for providing the computing services; evaluate one or more utility functions defining service level variables; and automatically determine a service level agreement (SLA) provision for the customer based on the one or more utility functions.

Abstract: In some aspects, a computer-implemented method for diagnosing an unfavorable mobile application user experience is described. The method may include retrieving user application interaction data from a mobile device, inter-correlating the user application interaction data, updating a user interaction database with the inter-correlated user application data, and diagnosing, via a processor operatively connected to the user interaction database, information indicative of a cause of the unfavorable user experience.

Abstract: A method is provided for building patterns with high level pattern topology requirements for deployment across multiple systems. The patterns are built based on pattern capabilities and configurations of the multiple systems. Such patterns can meet the desired pattern capabilities including high availability and/or continuous capabilities.