Abstract: A method and a system for using artificial intelligence (AI) techniques to generate actionable recourses for resolving constrained resource allocation problems that would otherwise be infeasible are provided. The method includes: receiving, from a user, a request for a resource allocation that includes information that relates to resources to be allocated; receiving information that relates to mandatory constraints with respect to the request; determining that an infeasibility exists with respect to fulfilling the request in a manner that satisfies each of the constraints, by applying an AI algorithm that uses a mixed-integer optimization technique for identifying at least one constraint that is impossible to satisfy; and generating an actionable recourse for facilitating a fulfillment of the request in a manner that overcomes the infeasibility.

Abstract: Systems and methods for redacted statement delivery to third-party institutions are disclosed. A method may include: receiving a request for a statement from a third-party backend; retrieving a list comprising a plurality of available statements; providing the list of the plurality of available statements to the third-party backend; retrieving a selection of one of the plurality of available statements; identifying metadata for data fields in a statement template; generate the selected statement using the statement template and embedding the metadata in data fields of the statement; identifying a redaction reason; identifying redaction metadata associated with the redaction reason; redact data fields in the statement having metadata matching the redaction reason metadata; storing the redacted statement in a temporary store; and returning a path for the temporary store to the third-party backend, wherein the third-party backend may retrieve the redacted statement from the temporary store.

Abstract: A contactless card may include: a first card portion and a second card portion; a manipulation area between the first card portion and the second card portion, wherein the contactless card may be manipulatable about the manipulation area; a chip storing information; and an antenna in communication with the chip comprising a first antenna portion in the first card portion and a second antenna portion in the second card portion, wherein the first antenna portion and the second antenna portion are electrically connected when the contactless card is in a first orientation such that the information can be read by radio frequency communication from the chip via the antenna, and the first antenna portion and the second antenna portion are electrically disconnected when the contactless card is in a second orientation such that the information cannot be read by radio frequency communication from the chip via the antenna.

Abstract: Systems and methods for counteracting data-skewness for locality sensitive hashing via feature selection and pruning are disclosed. In one embodiment, a method for feature selection for counteracting data skewness on locality sensitive hashing (LSH)-based search may include: (1) ingesting, by an ingestion computer program and from a plurality of data sources, data; (2) extracting, by the ingestion computer program, a plurality of features from the ingested data; (3) transforming, by the ingestion computer program, each of the plurality of features into a feature vector; (4) selecting, by the ingestion computer program, a subset of the plurality of features; and (5) for each selected feature vector: computing, by the ingestion computer program, a random hash function for the selected feature; and inserting, by the ingestion computer program, an output of the random hash function into a hash table with the selected feature.

Abstract: Various methods, apparatuses/systems, and media for automatically building an application framework are disclosed. An internal database stores available design patterns and code snippets for developing an application. A receiver receives, as input, a requirement document that includes one or more requirements for developing the application. A processor parses the requirement document by implementing a natural language processing algorithm; creates, based on the parsed requirement document, a plurality of code blocks for generating a structure and a design pattern to be used to develop the application by matching the one or more requirements with the available design patterns; accesses the database to obtain the code snippets for the plurality of code blocks; and automatically builds an application framework based on the code snippets.

Abstract: Various methods, apparatuses/systems, and media for data migration readiness of a target data source are disclosed. A processor hosts an application on a cloud server; receives data corresponding to the application from a plurality of types of data sources; defines expressions to be applied to the data for parsing and transforming the data dynamically on the cloud server; validates the defined expressions based on a determination that each defined expression meets a predefined threshold value; generates a lookup data file in a predefined file format in response to validating the defined expressions; parses the lookup data file; dynamically transforms the data based on the parsed lookup data file and applying the validated expressions; and generates an output file in the predefined file format for consumption after transforming the data.

Abstract: Systems and methods for one-click payments are disclosed. A method may include a backend for a financial institution: receiving, from a user electronic device, enrollment of a user in a payments process; generating a token comprising an identification of an API exposed to the backend; communicating the token to the user electronic device; receiving, from a content provider, enrollment of the content provider in the payments process; receiving, at the API, an identifier for the content provider, a cost for content provided by the content provider, and the user identifier; transferring the cost from the user account to the content provider account; and notifying the content provider of completion of the transfer, wherein the content provider is configured to make the content available to the user electronic device after completion of the transfer.

Abstract: A method and system for determining and mitigating a potential delay in task completion are disclosed. The method includes extracting previously resolved tasks and changes occurred to each of the previously resolved tasks, and calculating features for training a machine learning model. The method further includes dividing the tasks into different groups and training the machine learning model using the calculated features associated with the different groups. The method then starts a task and partially processes the respective task until reaching a cutoff time, and based on change history of the task up to the cutoff time and using the trained machine learning model, determines whether a delay is expected or not for the task.

Abstract: A method and system for dynamically customizing a webpage layout according to webpage transition history of a user are disclosed. The method includes collecting historical web session data of a plurality of users, and performing collaborative filtering using the collected historical web session data. The method further includes generating a probabilistic model and a webpage transaction path for a target user among the plurality of users. Then, the method further identifies one or more communities within the webpage transaction path, generates at least one recommendation and shortcut, and modifies a default webpage layout to include the at least one recommendation and the at least one shortcut.

Abstract: A system and a method for restricting the forwarding of voice data received by a smart phone device to virtual voice assistants that are accessible via the smart phone device are provided. The method includes: receiving information indicating that at least one criterion for restricting the forwarding of voice data is satisfied; and activating a module that is configured to disable virtual voice assistants that are associated with the smart phone device, such that each of the disabled virtual voice assistants is rendered inoperative. The criteria may include a presence of the smart phone device at a premises associated with a commercial entity, such as an employer of a user of the smart phone device, and the information may include an indication that an identification card has been swiped at a terminal located at the premises and/or geographical location data collected by the smart phone device.

Abstract: Various systems, methods, and media for facilitating selection of a transaction mode for an electronic transaction are provided. User identification information, that identifies a user of a user device that performs the electronic transaction, is obtained. User accounts are determined based on the user identification information. Location information of the user device is also obtained, and at least one of sound information detected by a microphone of the user device or light information detected by a camera of the user device is further obtained. A single merchant is determined based on the location information of the user device and the at least one of the sound information or the light information. The user accounts are analyzed, and a recommended user account is determined based on the single merchant. A notification to be displayed on the user device is generated based on the recommended user account.

Abstract: A method for preserving privacy with respect to modeling event sequence data is provided. The method includes: receiving information about a sequence of events; modeling the event sequence by a Hawkes process that has an intensity that includes an exogenous base intensity rate and an indigenous component that has an excitation rate and a decay rate; analyzing the received information; and determining estimated values of the exogenous base intensity rate and the excitation rate, such that an accuracy of the estimates corresponds to a length of time over which the sequence of events is observed. Differential privacy is introduced by adding noise to the sequence of events in order to preserve the privacy of individuals associated with the events, and a cost of the differential privacy is expressible as an additional length of observation time required to ensure the accuracy of the estimates.

Abstract: A method of driving SQL optimization in a relational database by anti-pattern analysis of dynamic performance characteristics is provided. The method includes receiving a SQL statement, analyzing execution plan of the SQL statement and other SQL runtime statistics, and detecting presence of any anti-patterns for the SQL statement. The method also presents a list of recommendations for remediation of the anti-patterns. The method further includes calculating a quality index value for the SQL statement by performing a weighted analysis of a number of attributes. When the quality index value of the execution plan is determined to be greater than or equal to the predetermined threshold value, the execution plan is sent to a production environment for execution. When the quality index value of the execution plan is determined to be less than the predetermined threshold value, the execution plan is sent to a client terminal for remediation.

Abstract: A method and system for providing a video query are disclosed. The method includes acquiring context information, training a first machine learning (ML) model using historical data of the software life cycle tool, and removing, by the first ML model, noise from the context information for generating a query including at least one keyword. Once the query is generated, executing, by a second ML model, the query to retrieve at least one video segment from a learning repository. Scoring and ranking is then performed on the at least one video segment. The ranked video segment is then transmitted, to the user interface of the software life cycle tool, and displayed in an ad-hoc manner.

Abstract: Various methods, apparatuses/systems, and media for automatically upgrading an application are disclosed. A processor creates a dynamic machine learning (ML) model; trains the dynamic ML model and scans for SDK upgrade for the application against the dynamic ML model by implementing ML algorithm for predictions. The processor executes the SDK upgrade in response to detecting that the training of the dynamic ML model is completed to trigger the processor to perform the following automated processes: implement the ML algorithm against the trained dynamic ML model to generate predictive results data for deprecated reference corresponding to the application; evaluate the predictive results data to determine whether there is a match for the deprecated reference; and when it is determined that there is a match for the deprecated reference, automatically replace code and upgrade the application to newer version of the programming language specification.

Abstract: A system and a method for performing an authentication are provided. The method includes: capturing, by using a front-facing camera of a mobile communication device, a first image of a face of a user; capturing, by using a rear-facing camera of the mobile communication device, a second image of an identification card that includes a photograph of the face of the user; comparing the first image with the second image; verifying that the first image matches the second image; obtaining user-specific information included in the second image; receiving a request to authenticate a transaction that relates to the user; receiving an input from the user that is usable for authenticating the transaction; and using the first image, the second image, the obtained user-specific information, and the received input to authenticate the transaction.

Abstract: A method may include a first party computer program: (1) receiving, a first real-time communication comprising a first offer for a first amount from a second party computer program; (2) partially accepting the first offer, causing first funds to be transferred to a second party account from a first party account; sending a second real-time communication to the second computer program comprising a partial acceptance of the first offer and a second offer for a second amount; (3) receiving, from the second computer program, partial acceptance of the second offer and a third offer for a third amount, causing second funds to be transferred to the second party account from the first party account; and (4) accepting the third offer, causing third funds to be transferred to the second party account associated from the first party account.

Abstract: A method and system for centrally modifying a rule in a product definition are disclosed. The method includes receiving, from a user, a change to a product subject to a set of rules, determining whether the change is incompatible with the set of rules, and when the change is determined to be incompatible with the set of rules, prompting the user to modify the change without storing the data associated with the change in a dynamic database residing on the cloud network. However, when the change is determined to be compatible with the set of rules, capturing data associated with the change in the dynamic database residing on a cloud network for first updating rules data, generating and uploading a data object as a microservice based on the first updated rules data, and versioning the product based on the set of rule objects associated with the product.

Abstract: System and method for generating time series forecasts based on probabilistic data are disclosed. A processor receives a request to identify at least one feature of a dataset that is most closely correlated to a single feature specified in the received request. The dataset includes the probabilistic data of the time series. The processor identifies a set of original features within the dataset and derives a degree of dependency between a single specified feature and each original feature by using a temporally first portion of the dataset. After deriving a degree of dependency between all the features including the single specified feature and each engineered feature of the set of original features, the processor identifies an original feature or an engineered feature with the highest degree of dependency as the at least one feature of the dataset that is most closely dependent to the single specified feature.

Abstract: Various methods, apparatuses/systems, and media for implementing a data book application module is disclosed. The processor identifies an application that needs to be scanned through a data factory; receives inventories of all servers and databases associated with the data factory; scans the servers and databases for receiving inventories of schema, tables and columns associated with the application; and applies artificial intelligence (AI) and/or machine learning (ML) routines and matching algorithms for matching contents of columns to predefined logical terms. The processor also converts the contents of columns into taxonomies associated with the predefined logical terms; matches the taxonomies with the corresponding predefined logical terms; assigns a probability of accuracy value to the matched terms; and populates a data catalog with the matched terms when the assigned probability of accuracy value satisfies a predetermined threshold value.