Abstract: A method of integrating electronic data including integrating a desktop such that the desktop includes information received from various sources. The information displayed may be analyzed by a business rule to prioritize what information is included in the desktop, and the information may include data from databases, recent member activities, planned future actions, and recommended future actions. The method also includes the ability to integrate and/or aggregate various data sources, such as databases. The combination of the data sources may be performed according to one or more business rules.

Abstract: The present disclosure generally relates to systems and methods for generating data representative of multi-product insurance discounts and related user interface displays. The systems and methods may include receiving personal data from an insurance customer and insurance product data. The systems and methods may further include generating data representative of multi-product insurance discounts based on personal data from an insurance customer and insurance product data. The systems and methods may further include generating displays of the multi-product discounts based on data representative of multi-product insurance discounts.

Abstract: There are provided systems and methods for cross-platform tracking of user generated data for unified data output. A computing device may be utilized to access an online platform and perform one or more processes, including viewing an online marketplace to purchase items in a transaction. The device may be used to browse items and items may be added to a digital shopping cart or other checkout process and interface. However, the device may not finish electronic transaction processing for the items and may abandon the digital cart on a first platform used by the user. When a user uses a second online platform to shop and generate another digital cart, a cross-platform process may retrieve the previously abandoned cart's data, and may generate output for display of the previous cart with the new cart in the second platform's user interface.

Abstract: A management system to facilitate improved software asset management includes a management server coupled to a client instance and certain databases. The client instance stores identifiers associated with software programs accessible to users through the client instance. To enable software asset management features, the management server receives the identifiers and determines, based on the certain databases, whether the identifiers are associated with software models of the software programs. Notably, in response to an identifier of a particular software program not being associated with a software model, the management server generates a software model for the particular software program, and further, stores entries or relationships within the certain databases.

Abstract: This application relates to apparatus and methods for identifying fraudulent transactions. The embodiments may employ machine learning processes to detect fraudulent activity. In some examples, a computing device determines customer data and device data for a customer and device involved in a transaction. The customer data may include previous transactions by the customer, and the device data may include previous transactions involving the device. The computing device generates features based on the customer data and the device data, and applies one or more machine learning models to the generated features to generate a trust score. The trust score is indicative of how likely a transaction is to be fraudulent. In some examples, the transaction is not allowed if the trust score is beyond a threshold. In some examples, the computing device trains the machine learning models based on customer data and device data for a plurality of customers and devices.

Abstract: Systems and methods include a group fund processor having a communications interface that receives account data associated with a primary account from a device over a network, creates a group fund account, and associate one or more limits with the group fund account, an alert interface that transmits an electronic invitation including a description of a first amount to an invited user and receives a response from the invited user to the at least one invitation, wherein the response includes account data associated with a respective group member account of the invited user; and an account processor that links the group fund account to the primary account, and links respective group member account of the invited user to the group fund account so that the first amount is transferred from the respective group member account of the invited user to the group fund account.

Abstract: A server computer system comprises a communications module; a processor coupled with the communications module; and a memory coupled to the processor and storing processor-executable instructions which, when executed by the processor, configure the processor to analyze historical data transfers within one or more resource accounts to generate a data budget; receive a signal indicating a data transfer request; analyze the data transfer request and, based on the data budget, determine an affordability of the data transfer; responsive to determining that the data transfer is not affordable from one of the resource accounts, generate one or more recommendations to afford the data transfer; and send, via the communications module and to a computing device, a signal causing the computing device to display a notification that includes the one or more recommendations to afford the data transfer.

Abstract: A method may include presenting a user interface (UI), to a user, in a first mode on a client device, the UI including a list portion, the list portion including a plurality of transactions associated with respective activity on a user account, and the client device including an input device; receiving an indication of a first user action on a transaction presented in the list portion of the UI; in response to receiving the indication, updating a section of the list portion corresponding to the transaction, the updating including revealing a set of options for the transaction; receiving an indication of a second user action corresponding to activation of an option of the set of options; and in response to receiving the indication of the second user action, transitioning the UI from the first mode to a second mode, the second mode including a chatbot interface instantiated with respect to the transaction.

Abstract: The present disclosure provides a currency settlement method and apparatus. The currency settlement method includes: settling with a mining node that acquired a first virtual currency according to a workload performed by the mining node and an income type of the mining node; according to a settlement currency type, transacting with an exchange institution to exchange an amount in the first virtual currency into an amount in a second virtual currency, the second virtual currency being the settlement currency type; and transferring the amount of the second virtual currency to an account.

Abstract: A system for interfacing predetermined services to a user at a fixed location includes a processing platform running an operating system. The system further includes a data store for storing configuration information for enabling the operating system to interface with available physical system resources through the physical system resource interface associated therewith. A communication resource for interfacing with the operating system allows communication of the operating system with a central office for downloading configuration information to selectively enable ones of the available physical system resources to interface with the operating system through associated ones of the physical system resource interfaces in accordance with the configuration information and the predetermined service selected by a user. A plurality of configurations is stored in the data store, and each is associated with a predetermined service and one or more of the available physical system resources.

Abstract: A computer-implemented method for providing personalized purchasing information to a user may include: obtaining first identification data of the user from a first engine; verifying a registration status of the user based on the first identification data; obtaining second identification data of the user from a second engine based on the registration status of the user; comparing the first identification data of the user and the second identification data of the user; initiating a real-time credit monitoring session based on the comparison between the first identification data of the user and the second identification data of the user; generating the personalized purchasing information of the user based on the real-time credit score of the user; and demonstrating the personalized purchasing information on a display of a device associated with the user.

Abstract: A digital platform and system that provides an automated, multi-channel, end-to-end risk-transfer configuration and/or parametrization process for configuring, launching, and processing of customized second-tier transfer structures, wherein an automated risk-transfer placement for objects or property assets each having a geographic location related to occurrence of physical impacting risk-events, the objects or property assets impacting events, is provided by the digital platform and system as a first online channel comprising an electronic, parameter-driven, rule-based underwriting process for automatically creating a portfolio or composition of customized second-tier structures. An automated claim handling is provided by the digital platform and system as a second online channel, and automated accounting is provided by the digital platform and system as a third online channel.

Abstract: Various embodiments are generally directed to techniques for accurate evaluation of a financial portfolio. Techniques described herein may include an apparatus comprising: a processing circuit; and an approximate computing engine, executed on the processing circuit, operative to process data items corresponding to prices of funds, compute a Net Asset Value (NAV) based on the data items, determine a precision associated with the Net Asset Value (NAV), and based upon a precision metric, determine whether to use the Net Asset Value (NAV) in a business decision. Other embodiments are described.

Abstract: A computing device is configured to acquire or access credit or reporting data associated with a consumer. The computing device then is configured to analyze the credit or reporting data to determine reporting cycles for accounts associated with the consumer. For example, the computing device may determine that credit information for a particular account may be updated at a regular interval (e.g., once a month on the 3rd) or some other more complex cycle. The computing device can subsequently used the determined reporting cycles to predict the next reporting dates for respective accounts and provide the information, for instance, to the consumer.

Abstract: The present disclosure provides a management method for software versions to improve transaction safety of software. In the management method, among management apparatuses, a first token management apparatus obtains request information indicating a requested version requested by a user, and first transaction data indicating that the user provides predetermined number of tokens to a software developer who has developed the requested version is stored in distributed ledgers through execution of a consensus algorithm by the management apparatuses.

Abstract: A method and system may use computer vision techniques and machine learning analysis to automatically identify a user's biometric characteristics. A user's client computing device may capture a video of the user. Feature data and movement data may be extracted from the video and applied to statistical models for determining several biometric characteristics. The determined biometric characteristic values may be used to identify individual health scores and the individual health scores may be combined to generate an overall health score and longevity metric. An indication of the user's biometric characteristics which may include the overall health score and longevity metric may be displayed on the user's client computing device.

Abstract: A system and method for guiding a user after an accident and gathering relevant data for an insurance claim and/or a coverage determination. The system includes a mobile device having a memory element, processing element, communication element and user interface. The mobile device may also include a sensor and/or global positioning system. The user interface and/or sensor of the mobile device (e.g., microphone. UPS, camera, etc.) may receive information relevant to an insurance claim, including by directing a user to capture images of relevant objects and/or querying the user for verbal description(s) of facts regarding the accident. The information gathered may be saved on the memory element of the mobile device. The information may also be transmitted to a server via a network in the form of a structured incident data report.

Abstract: An automated method of predictive model development first cleans up raw supervised and unsupervised training data with a step that uses an algorithm to make every field of every record consistent, cohesive, and productive. Then the resulting flat data is given texture in a next step by a data enrichment algorithm that culls fields that do not contribute to predictive model building and that adds new fields computed from data combinations that are tested to add value to later steps that build different types of predictive models. Another late step for building smart-agents and their entity profiles uses another algorithm that benefits greatly from the cleaned and highly enriched training data. The predictive models and smart-agents and their entity profiles are then rendered as deliverable predictive model markup language documents in a final step executed by a specialized algorithm.

Abstract: Embodiments of the systems and methods of using the same are configured to provide a financial solution product for customers seeking financing and advice for debt consolidation, home improvement, financing for school loans, finding the right credit card, and financing collateral. The systems and methods provide a means to dynamically calculate multiple financial solution products and present them to a user.

Abstract: In some examples, a system may receive transaction data indicating payments into a first account over time and payments out of the first account over time, the first account associated with a user. In addition, the system may access a data structure including historical account data that indicates variations in a balance of the first account over time. The system may determine an indicated minimum balance for the first account based on inputting the transaction data and the historical account data into a first predictive model configured to predict a minimum balance for enabling predicted payments out of a user account. The system may determine, based on a difference between a current balance of the first account and the predicted minimum balance for the first account, that the first account has a surplus of funds. Based at least on the surplus, the system may send an instruction.

Abstract: A reward card platform includes a database storing funding accounts, reward card purchase transactions, and aberrant activity rules. A first user interface enables purchasing reward cards, including controls to specify reward card parameters. A second user interface enables specifying rules to detect aberrant activity. The second user interface includes user interface controls to specify the rule parameters, including: specifying a moving window of time; specifying an aggregation type; specifying filtering; specifying aggregation grouping; and specifying a threshold value for triggering an alert. The platform includes a rules execution engine that runs periodically to evaluate each of the rules. For each rule, the engine identifies transactions whose timestamps fall within the moving window of time relative to a current time and satisfies the filters, then computes an aggregation of the transactions according to the aggregation type and aggregation grouping.

Abstract: An industrial automation system includes a collector component communicatively coupled to a first network and configured to receive one or more event logs via a first communication protocol. The industrial automation system also includes a first industrial automation component communicatively coupled to the first network and the collector component. The first industrial automation component is configured to communicate via the first communication protocol. Additionally, the industrial automation system includes a second industrial automation component configured to communicate via a second communication protocol, generate a first event log representative of a property associated with the second industrial automation component, and send the first event log to the first industrial automation component.

Abstract: A network computing system to provide an account management service for guiding user actions and providing users with information to facilitate decision making. In providing the account management services, the network computer system makes predictive determinations about the actions of service providers, in connection with specific actions of individual users.

Abstract: A system and method for integrating a widget in a third-party application. Initially, a widget software code related to insurance payment capture and verification may be received. Further, the widget software code may be integrated into an application code of a third-party application. The widget software code may be executed to invoke an insurance payment widget. The insurance payment widget is configured to capture insurance card images, and extract insurance information based on an analysis of the insurance card images. Furthermore, the extracted insurance information may be validated using an insurance database and plans curated by an application provider. Subsequently, an insurance eligibility status and insurance coverage benefits of the insurance subscriber may be received and used to enable an insurance payment mode on the third party application in real-time, thereby integrating the widget in the third party application.

Abstract: A specialized computer matching system programmed to match orders for financial instruments of any type; where orders are matched at a price equal to the best available price or within the best available prices in the market; where priority of matching orders is ranked by price; where orders at the same price may be further ranked based on other attributes; where orders may optionally specify that the order sender is willing to pay a fee to (or receive a rebate by) an Order Matching Entity (i.e., a fee/rebate contingency (FRC)); where an order's optional FRC must be met in order to match the order; and where an order which cannot be matched solely because its FRC rate prevents it from matching with another order temporarily yields priority—other than price priority—to other orders ranked below to permit those orders to be matched.

Abstract: Systems and methods for providing analytics data to payment facilitators and sub-merchants via a dynamic dashboard, in response to receiving transaction data from one or more Internet of Things (IoT) devices. In one implementation, a method includes receiving transaction data and a unique identifier of a sub-merchant, analyzing that data, and transmitting an unrequested analytics report to a dashboard.

Abstract: Based on the interaction data and response data, an interaction monitoring platform may determine a first known sentiment and a second known sentiment, identify a first pattern and a second pattern in the interaction data, and generate a first pattern-level sentiment and a second pattern-level sentiment based on the known sentiments and the identified patterns. A binary indicator may indicate which identified patterns are exhibited in a subset of the interaction data. The platform may train a gradient boosting model using known sentiment as a target variable and using binary indicators and pattern-level sentiments as input data. The platform may predict a sentiment corresponding to a subset of interaction data with unknown sentiment that exhibits one or more of the first pattern or the second pattern based on a binary indicator and the trained gradient boosting model.

Abstract: Various examples described herein are directed to systems and methods for generating a financial account statement. First financial data associated with a first financial account statement for a customer is received, Second financial data associated with a second financial account statement for the customer is received. The first financial data may be from an earlier financial account statement. Changes between the first financial data and the second financial data are determined. Highlighted changes to augment based on preferences of the customer and the determined changes are determined. Content associated with the highlighted changes is determined. The second financial account statement is created based on the second financial data. The content associated with the highlighted changes is linked in the second financial account statement.

Abstract: An authentication server computing device is provided. The authentication server computing device is configured to receive a transaction request from an audio interface device, generate a first audio file including a first audio transmission, wherein the first audio transmission includes a primary security artifact and at least one secondary security artifact and the primary security artifact is an encoding of a one-time password, store a reference data file including the first audio transmission, transmit the first audio file to a verified user computing device associated with the account identifier, receive a second audio file from the audio interface device, wherein the second audio file includes a second audio transmission, verify the second audio transmission by comparing the second audio transmission to the reference data file including the primary security artifact and the at least one secondary security artifact, and authorize the transaction based on verifying the second audio transmission.

Abstract: A service tracking and guidance system includes processing circuitry configured to receive, from a location tracking device and/or an online service, usage data indicative of usage of a service by a consumer. The processing circuitry is also configured to determine a usage value based on the usage data, to receive remittance data indicative of recurring payments made by the consumer for the service, and to retrieve a usage threshold that represents a level of usage of the service that justifies the recurring payments. The processing circuitry is further configured to compare the usage value determined based on the usage data for a time period that corresponds to at least one of the recurring payments to the usage threshold and to provide an output with directions to increase the usage value or to facilitate cancellation of the service in response to the usage value being below the usage threshold.

Abstract: Embodiments of the present disclosure provide for reduced-reliance onboarding with respect to a service provider application, including but not limited to vehicle service provider applications. Embodiments provide a custom onboarding message that enables onboarding of at least one data object via access, by a user device, of the custom onboarding message with reduced-reliance. Example embodiments receive, from a provider system, acquisition data including at least user communication channel data usable for transmitting information to a user device associated with the customer, generating a subject data object comprising at least a portion of the subject information, attempting initiation of an custom onboarding message to be accessed by the user device associated with the customer, receiving an indication that the customer accessed the custom onboarding message via the user device, and updating data associated with the subject data object to indicate completion of onboarding.

Abstract: The invention teaches a value exchange for natural resources that is transparent and assured by a layer of distributed trust where tokenized inventory collateralizes derivative products, which enables the inventory to be monetized while located anywhere in the world including in major buying hubs, whereby suppliers, buyers and market makers can execute and settle authenticated transactions, both outright sales and derivative transactions, for natural resources in near real time.

Abstract: An example method of reimbursing pharmacy-related transactions includes receiving first data describing a transaction between a patient and a pharmacy. The transaction includes dispensing of a medication. A reimbursement data packet is determined based on the first data. The reimbursement data packet includes second data describing a reimbursement claim to be submitted to a payer system for the transaction. The reimbursement data packet is transmitted from the computer system to a plurality of other computer systems. A response is received from each of the other computer systems. Each response indicates whether a respective one of the other computer systems determined that the reimbursement claim is valid. A determination is made that the reimbursement claim is valid based on the responses. An entry describing the transaction and reimbursement claim is added to a ledger, and the reimbursement claim is submitted for fulfillment.

Abstract: Certain embodiments of the disclosure relate to methods and systems that support automated, targeted polling of consumers via an e-commerce promotions platform for administering e-commerce promotional activities, such as, for example, sweepstakes, contests, giveaways, and/or instant wins.

Abstract: Systems and methods are disclosed with respect to using a blockchain for managing the subrogation claim process related to a vehicle collision, in particular, utilizing evidence oracles as part of the subrogation process. An exemplary embodiment includes receiving recorded data from one or more connected devices at a geographic location; analyzing the recorded data, wherein analyzing the recorded data includes determining that an collision has occurred involving one or more vehicles; generating a transaction including the data indicative of the collision based upon the analysis; and transmitting the transaction to at least one other participant in the distributed ledger network.

Abstract: Systems, methods, and devices are presented for providing and managing investments and workflow for investors and sponsors are described. The system provides and utilizes an actionable, reliable, transparent, real-time, collaborative marketplace for facilitating funding and distribution and for reviewing the performance of private placements via an online, authoritative, unified compliance and execution platform for private placements and other investments.

Abstract: A method includes acquiring blockchain data that includes transactions between a plurality of blockchain addresses. The method includes labeling a set of the blockchain addresses as fraudulent and generating a graph data structure based on the blockchain data. The method includes calculating a set of scoring features for each blockchain address, where each set of scoring features includes a graph-based scoring feature. Calculating the graph-based scoring feature includes calculating a number of transactions associated with the blockchain address in the graph data structure. The method includes generating a scoring model using sets of scoring features for the blockchain addresses that are labeled as fraudulent and generating a trust score for each blockchain address using the scoring features and the scoring model. The trust score indicates a likelihood that the blockchain address is involved in fraudulent activity. Additionally, the method includes sending a requested trust score to a requesting device.

Abstract: Transaction systems and methods are disclosed. A system may include a controller having a transaction detection circuit to interpret a transaction request value, wherein the transaction request value includes a transaction description for one of a proposed or an imminent transaction, and a cryptocurrency type value and a transaction amount value. A transaction locator circuit then determines a transaction location parameter in response to the transaction request value, wherein the transaction location is a geographic value or a jurisdiction value. A transaction execution circuit then provides a transaction implementation command in response to the transaction location parameter.

Abstract: Provided is a system for conducting a payment transaction involving payment on delivery in real-time. The system may include at least one processor programmed or configured to receive transaction data associated with a payment transaction involving a merchant and a customer at a location that is independent of a merchant location, determine a financial institution of a plurality of financial institutions based on the transaction data associated with the payment transaction, communicate data associated with a request for authorization of the payment transaction involving the merchant and the customer, receive an indication of authorization of the payment transaction involving the merchant and the customer, and communicate data associated with authorization of the payment transaction involving the merchant and the customer. A method and computer program product are also provided.

Abstract: The present disclosure provides a composite machine learning system for a transaction labeling service. A transaction labeling service receives at least one descriptive string describing a transaction associated with a user. The service identifies a preliminary grouping from a generalized scheme. The service extracts a set of N-grams from the descriptive string and converts the N-grams and the preliminary grouping into a set of features. A machine learning model determines a label from a labeling scheme for the transaction based on the features. User input related to the label includes an accuracy indicator and a reliability indicator. If the reliability indicator satisfies a reliability condition, a set of training data for the machine learning model is updated based on the descriptive string and the label. The machine learning model is then trained against the updated set of training data.

Abstract: Provided herein is a method for delivering web content to a computer user where the computer user must provide data for verification. A control presented by a first web page provided by a requesting server of a requesting party may be selected to request a further web page where data may be entered that requires verification. The requesting server may redirect the computer user to a verifying server that may provide a second web page to fulfil the request for the further web page. The second web page may be presented as a foreground window positioned over a backdrop frame. The foreground window may be provided with fields for entering the data and the backdrop frame may be provided by the requesting party. The verifying server may verify data entered in the foreground window and may send the requesting server a notification as to whether the verification was successful.

Abstract: Systems and methods for secure payment processing are disclosed. An issuer vault generates payment items, which correspond to consumer account information and which replicate the structure of the account information but do not include consumers' actual account number. The payment items, rather than the actual account information, are communicated to on-line and mobile payment services for use by consumers in payment transactions. When a consumer uses a payment item in a payment transaction and the transaction undergoes authorization processing, the payment authorization network uses the payment item to request and receive the actual account information from the issuer vault. The authorization network uses the actual account information for the limited use of authorizing the transaction. Once the transaction has been authorized using the actual account information, the processing of the transaction continues using the payment item information rather than the actual account information.

Abstract: The computer networks provided herein may facilitate the delivery of interactive data units to selective client nodes. A client node may be associated with, and/or be accessible by, a user. The interactive data units received at a client node may be activated by the user associated with the client node. In some instances, a computer network may facilitate delivery of an interactive data unit to a client node based on the user, and/or user information, associated with the client node.

Abstract: A computerized analysis system includes a data retrieval module, a spike filter module, a chargemaster analysis module, and an alert module. The data retrieval module is configured to retrieve claimline data for a period of time from an input data store. The claimline data includes billing codes and prices of the billing codes associated with a provider. The spike filter module is configured to flag and filter price spikes in the claimline data. The chargemaster analysis module is configured to determine whether a changepoint exists in the billing codes in the claimline data. The chargemaster analysis module is configured to identify a chargemaster increase for the provider in response to a statistical parameter of changepoints exceeding a threshold. The alert module is configured to, in response to identification of a chargemaster increase, publish an alert that a chargemaster increase has occurred for the provider.

Abstract: The invention relates to database abstraction and data linkage. According to an embodiment of the present invention, the invention takes a variety of attributes (e.g., names, IP address, device identifiers, addresses, phone numbers, account numbers, etc.) and returns the online activity, demographic data, account data and/or other activity, events and data associated with that attribute. The tool may then iterate over each attribute and return a network of connections having multiple degrees of association. The innovative tool may be linked to known bad actor data, and perform automated searches on this data to proactively alert potentially fraudulent activity. The tool may also be developed to add attributes and apply machine learning to the associations to more intelligently describe the returned network. Further, the tool may be developed to describe larger networks having multiple degrees of connections.

Abstract: A computer system accesses electronically stored data pertaining to a consumer's current and historical credit reports from a plurality of credit bureaus. Errors in the reports are identified by the computer system, which can then create dispute letters detailing the errors with text customized for each error. The computer processes the data to identify errors within a single report and between multiple reports, both current and historical. The errors can relate to multiple accounts on a given report duplicating the same debt with the same or differing status, and reports from different credit bureaus reporting the same debt with differing status. The status can include the debt being open or closed, and the date a status of the debt changed. The errors are presented on a display with which particular errors can be selected to be included in the report.

Abstract: Real-time prevention of computerized event manipulation through the use of Artificial Intelligence (AI)-assisted quantum computing. Determine, at an event request time, if the event is being manipulated and/or is part of a manipulation scheme and, if so, prevent the event from being initiated. A classical computing platform analyzes a batch of historical events using AI including machine learning classification algorithms to result in a manipulation indicator for each of the historical events. A quantum computing platform converts each of the historical events in the batch to a qubit sequence based on attributes associated with the events. The qubits are entangled with qubits of a primary qubit sequence and maintained an entangled list. When an event is requested, attributes associated with the pending event are communicated to the quantum computing platform, which transforms/converts the pending event to the primary qubit sequence based on the attributes associated with the pending event.

Abstract: An analysis system includes a data retrieval module that retrieves claimline data for a period of time. The claimline data includes multiple billing codes and corresponding prices associated with a provider. An analysis module receives the claimline data from the data retrieval module, determines whether a changepoint exists in the billing codes in the claimline data, determines a statistical parameter of changepoints per day during the period of time, and identifies a chargemaster increase for the provider in response to the statistical parameter of changepoints exceeding a threshold. An alert module, in response to identification of a chargemaster increase, publishes an alert that a chargemaster increase has occurred. The alert includes the provider's identification, a chargemaster increase date, a claimline number, a changepoint number, the billing code identification, or a price of the billing code at the changepoint. The alert transforms a user interface displayed to a user.

Abstract: Systems and methods for forecasting cashflows across one or more accounts of a user disclosed. One example method may include retrieving a data set for each of a plurality of accounts from a database, constructing a graph including a plurality of nodes linked together by a multitude of edges, wherein each node identifies a time series value corresponding to one of the accounts, and each edge indicates a time series value of a corresponding set of transactions occurring between a corresponding pair of accounts, determining a plurality of constraints, determining a specified loss function based on the plurality of constraints, back-propagating a derivative of the specified loss function into a deep neural network (DNN) to determine a set of neural network parameters, forecasting, using the DNN, a time sequence for one or more of the nodes and one or more of the edges, and providing the forecasted time sequences to the user.

Abstract: A method of the present disclosure includes a host system authenticating a user of the user device to access secure host information associated with the user in a database. A request may be transmitted to a third-party system to access secure third-party information stored by the third party based on third-party authentication information. The host system may receive the secure third-party information and store the secure third-party information in a memory location of the database that is associated with a different memory location including the secure host information. The memory location and the different memory location may be associated in the database based on a common information type. The host system may generate a graphical user interface that positions the secure host information and the secure third-party information in the graphical user interface based on their respective location in the database.