Abstract: Examples described herein relate to systems, apparatuses, and methods for generating a securitized loan blockchain, including providing at least one security criterion, identifying at least one loan block of a loan blockchain that satisfies the security criterion, where the loan blockchain corresponds to at least one loan, and the security criterion is associated with the at least one loan block and a dynamic financial profile of a borrower of the at least one loan, and generating a security blockchain including at least a first security block, where the first security block is associated with a loan link identifier object that identifies the loan block of the loan blockchain.

Abstract: A system and method for automated blockchain custody service for managing a set of custodial assets with block chain authenticity verification is disclosed.

Abstract: Systems and methods for automated servicing of a subsidized loan are disclosed. An example system may include a crowdsourcing services circuit to collect information related to a set of entities involved in a set of subsidized loan transactions and a condition classifying circuit including a model and an artificial intelligence services circuit to classify a set of parameters of the set of subsidized loans based on information from the crowdsourcing services circuit, where the model is trained using a training data set of outcomes related to subsidized loans. The example system may further include a smart contract circuit for automatically modifying a term or a condition of the subsidized loan based on the classified set of parameters from the condition classifying circuit.

Abstract: This invention relates generally to data assembly and analytics, as can be used in the personal finance and banking field, and more particularly to the field of lending and credit notification methods and systems. Preferred embodiments of the present invention provide systems and methods for creating objects which can be used in multiple implementations to generate scores.

Abstract: This present disclosure provides a risk assessment method and system for affordable housing application in a smart city based on Internet of Things. The risk assessment method is executed by the management platform, and the risk assessment method includes obtaining a query request for a risk of the affordable housing application from the service platform, wherein the query request is generated by the user platform based on an input of the affordable housing application by an applicant through the user platform; in response to the query request, through a management sub-platform corresponding to the management platform and a service sub-platform corresponding to the service platform, obtaining relevant information of the applicant and his/her related persons thereof, and determining the risk of the affordable housing application of the applicant; and sending the risk of the affordable housing application to the service platform.

Abstract: A first set of execution platforms is deployed for a set of operations of a training phase of a machine learning model. Prior to the completion of the training phase, a triggering condition for deployment of a different set of execution platforms is detected. The different set of execution platforms is deployed for a subsequent set of training phase operations.

Abstract: A pervasive advisor for major purchases and other expenditures may detect that a customer is contemplating a major purchase (e.g., through active listening). The advisor may assist the customer with the timing and manner of making the purchase in a way that is financially sensible in view of the customer's financial situation. A customer may be provided with dynamically-updated information in response to recent actions that may affect an approved loan amount and/or interest rate. Underwriting of a loan may be triggered based on the geo-location of the user. Financial advice may be provided to customers to help them meet their goals using information obtained from third party sources, such as purchase options based on particular goals. The pervasive advisor may thus intervene to assist with budgeting, financing, and timing of major expenditures based on the customer's location and on the customer's unique and changing circumstances.

Abstract: Systems and methods for using social network data to validate a loan guarantee are disclosed. An example system may include a social networking input circuit to interpret a loan guarantee parameter; a social network data collection circuit to collect data using a plurality of algorithms that is configured to monitor social network information about an entity involved in a loan in response to the loan guarantee parameter; and a guarantee validation circuit to validate a guarantee for the loan in response to the monitored social network information.

Abstract: A computer-implemented method and apparatus are provided to reduce false fraudulent declines of transactions. Payment processor (PP) systems may be provided with a request acceptor and a replacement transaction generator. The request acceptor receives a notification of a decline of a first transaction attempted by a cardholder with a merchant, for allegedly fraudulent, and a request to determine whether the first transaction was falsely identified as fraudulent, and if so, to remedy the first transaction. The replacement transaction generator generates, in response to a determination that the first transaction was falsely identified as fraudulent, and the merchant is a false fraudulent reduction partner merchant, a replacement second transaction to replace the declined first transaction. The replacement second transaction may include a bypass authorization code, and made available to the cardholder to use to transact with the merchant bypassing the declined first transaction.

Abstract: A method and an apparatus for identifying a transaction risk are disclosed. The method includes obtaining risk identification information of a sub-network to which a node relating to a transaction to be identified belongs; and identifying a risk of the transaction to be identified based on the risk identification information of the sub-network to which the node relating to the transaction to be identified belongs, wherein the sub-network is a network acquired by partitioning a relationship network based on connectivity, the relationship network is a network built up with entities and activities relating to a plurality of transactions.

Abstract: Disclosed is a method of establishing and managing an inter-institution transaction system. The method comprises creating plurality of threads to constitute parallel fund transfer system, wherein each thread is a replica of single fund transfer system, and wherein plurality of threads are to be operated in parallel; assigning plurality of institutions to plurality of threads, wherein a given institution is assigned as a sending institution and/or a receiving institution of a financial transaction to at least one thread, and a given thread has at least one sending institution-receiving institution pair assigned thereto; assigning financial transactions to plurality of threads based at least on sending institution-receiving institution pairs assigned to plurality of threads; and processing financial transactions at their corresponding threads.

Abstract: A computing device may include a provider application and data defining perceptible elements that provide users with various functionalities in more easily consumable stages. The application may determine that the user is at a first level of sophistication based on user activities and/or circumstances, and present a first set of perceptible elements in response thereto to provide a first set of functionalities. The application may then determine the user is at a second, higher level of sophistication based on subsequent activities and/or circumstances, and present a second set of perceptible elements to provide a second set of functionalities that includes at least one new functionality not provided via the first set of perceptible elements. Applications can be less resource intensive by evolving to strategically tailor available functionality to the circumstances and needs of particular users.

Abstract: A payment gateway is configured to directly access a revenue stream and financial information about the revenue stream. A machine learning (ML) model is trained to continuously process the financial information about the revenue stream to continuously analyze and score the revenue stream. A smart contract factory is responsive to the scoring by the ML model to generate at least one smart contract on a distributed, decentralized network. The smart contract is programmed to receive payments in stablecoins with respect to revenue stream.

Abstract: A method for detecting a fraud attempt in a communication session may include receiving, via at least one processor, a set of data associated with a communication session between a representative of an organization and a user, tagging, via the at least one processor, one or more items of the set of data as one or more tagged data items, applying, via the at least one processor, a fraud detecting algorithm to the one or more tagged data items to determine a percent likelihood of the user attempting to defraud the representative, generating, via the at least one processor, a visualization based on the percent likelihood, and displaying, via the at least one processor, the visualization via an electronic display during the communication session.

Abstract: The disclosure describes embodiments of systems, methods, and non-transitory computer readable storage media that increase a base limit value for a contact based on a user interaction with a graphical user interface. Generally, the disclosed system provides a graphical user interface for display to a user that includes base limit increase elements to increase base limit values for contacts of the user. Based on user selection of a base limit increase element, the disclosed system can provide an increased base limit value to an account associated with the contact.

Abstract: Systems and methods configured for monitoring and analyzing financial transactions on public distributed ledgers for suspicious and/or criminal activity are disclosed. Exemplary implementations may: access public third-party information for addresses involved in financial transactions; correlate a first portion of the public third-party information with transaction addresses; label the financial transactions and/or the addresses according to characteristics, such that individual ones of the addresses either have been labeled or are unlabeled; cluster the financial transactions and/or the addresses into a set of clusters that includes a first cluster; assign levels of risk for suspicious and/or criminal activity to the addresses and the financial transactions; and responsive to comparisons of levels of risk with a threshold, report transactions for suspicious and/or criminal activity.

Abstract: This disclosure describes techniques for analyzing operational data and applying one or more rule sets to identify issues and/or to determine whether action should be taken to prevent or mitigate a future risk event. In one example, this disclosure describes a method that includes receiving, by a computing system, risk data; generating, by the computing system and based on the risk data and a set of rules, an issue relating to an entity; outputting, by the computing system, a request; responsive to outputting the request, receiving, by the computing system, a response to the issue from the entity; storing, by the computing system, information about the response; receiving, by the computing system, information about a risk outcome associated with the issue; and modifying, by the computing system and based on at least one of the response and the information about the risk outcome, the set of rules.

Abstract: A plurality of liability factors of an asset is identified. Each liability factor impacts a total liability of the asset. A magnitude of a predetermined magnitude scale is identified for each of the plurality of liability factors according to a predetermined magnitude scale. Each magnitude is graphically encoded into a liability image for the asset. A risk score of the asset is determined by analyzing historical correlations between respective magnitudes of the plurality of liability factors using image recognition techniques on the liability image.

Abstract: A system for interfacing with a decisioning service from a third-party domain. A backend system may receive a request to interface with the decisioning service to generate a prequalification result for a user for a specified product, in response to the actuation of a button included in a third-party web domain rendering a product. The backend system may execute a call on a website of the decisioning service. The backend system may receive the product information from the button. The backend system may generate the website within the third-party domain, including a request for information about the user, in response to executing the call to the website. The backend system may transmit a request for generating prequalification result for the product to the decisioning service. The backend system may receive the prequalification result from the decisioning service.

Abstract: A method of exercising effective influence over future occurrences using knowledge synthesis is described. Techniques include influencing methods that yield actions, once a proposed outcome has been assumed. This is different from methods, typically referred to as “predictive” or “prescriptive” that use analytics to model future results based upon existing data and predict most likely outcome. One or more methods of analysis of historical data, in a hierarchical manner, determine events which led to an observed outcome. The outcome-based algorithms use, as input, a future event or state and generate attributes that are necessary precursors. By creating these attributes, the future can be affected. Where necessary, synthetic contributors of such attributes are also created and made to act in ways consistent with generating the assumed outcome. These contributors might be called upon respectively, to post favorable opinions, to report balmy weather, or to describe sales to a certain population demographic.

Abstract: The present disclosure involves systems, software, and computer implemented methods for generating new credit accounts for immediate availability for use in current online transaction. One example process includes identifying, at a merchant application, a request to perform a credit application process associated with a particular user via a client application. The credit application process is associated with a financial institution, and the merchant application stores a set of user accounts, each associated with a merchant-specific identifier identifying the particular user profile at the merchant. An interactive application is presented within the merchant application, and information associated with the completed application is transmitted to an API associated with the financial institution with the merchant-specific identifier of the associated user.

Abstract: A computer-implemented system and method for managing and visualizing financial transaction data is disclosed. Rows of financial data are managed as data objects with a reorganizable node tree hierarchy. A user interface visualization system supports an interactive user interface with a client device. In some implementations, a user may reorganize the node hierarchy, define dimension, communicate on a node-based basis, and assign directly responsible individuals to nodes.

Abstract: Embodiments of the present disclosure relate to a data analysis system for grouping and enriching data items for presentation to an analyst through a user interface. Data items from one or more data sources are combined into memory-efficient clustered data structures, which may be stored as one or more data tables in a database. Analysis and scoring of those clustered data structures can be performed by utilizing various criteria or rules to generate scores, reports, alerts, or conclusions that may aid an analyst in evaluating the clustered data structures. The analysis and scoring may also be added to the clustered data structures which are stored as one or more data tables in a database. The analyst may be prompted to create a dossier format or specification and to additional enrichments to be performed on the raw data items in the clustered data structures.

Abstract: System, apparatus, user equipment, and associated computer program and computing methods are provided for facilitating efficient decision-making with respect to a subject entity. In one aspect, a labeled training dataset containing N records respectively corresponding to N entities is provided for training a decision engine based on performing supervised learning. Responsive to receiving a plurality of attribute values for the subject entity requiring a decision relative to an estimate of a performance variable based on at least a portion of the attribute values, the trained decision engine is configured to determine a decision score as a function obtained as a set of linearly decomposed constituent components corresponding to the attribute values of the subject entity, thereby effectuating an objective determination of which attributes contribute to what portions of the decision score in a computationally efficient manner.

Abstract: A search request may define a minimum value and a maximum value for a numerical parameter of the search. A plurality of binary searches may identify a minimum entry and a maximum entry, each binary search comprising selecting a single entry and using at least one analytical model to generate a score for the single entry, wherein the score of the minimum entry corresponds with the minimum value and the score of the maximum entry corresponds with the maximum value. The at least one analytical model may be used to generate a score for each of a set of entries between the minimum entry and the maximum entry while ignoring entries outside of the set of entries between the minimum entry and the maximum entry. Entries responsive to the request may be identified within the scored set of entries.

Abstract: Embodiments for entity transaction interaction analysis and summarization by a processor. Transaction elements relating to one or more entity transaction interactions may be identifies and extracted from one or more communications. The transaction elements may be combined with one or more transaction opportunities and transaction historical data to provide a transaction summary.

Abstract: Distributed ledger-based networks (DLNs) employ self-executing codes, also known as smart contracts, to manage interactions occurring on the networks, which may result in the generation of a massive amount of DLN state data representing the interactions and participants thereof. The instant disclosure discloses systems, apparatus and methods that allow interactions to occur on the DLNs without modification to stored data, thereby improving the storage capabilities of the networks.

Abstract: Disclosed herein are system, method, and computer program product embodiments for identifying and managing emerging risks. Businesses, such as those participating in regulated industries, may need to regularly monitor enforcement actions that are cited in a variety of sources. Embodiments disclosed herein provide for scraping information from those sources and comparing it to existing risk events in order to determine possible discrepancies that should be assessed.

Abstract: Systems, methods, and computer program products to provide credit decisioning based on graph neural networks. A lending network graph of a plurality of loans may be received, each loan associated with a creditor and one account. A first node of the graph may be associated with a first creditor and the second node may be associated with a first account. A graph neural network may receive a respective message from each node connected to the first node, each message comprising an embedding vector reflecting a current state of the node. The graph neural network may update weights for the first node in a forward pass. The graph neural network may receive a respective message from each node connected to the second node, each message comprising the embedding vector reflecting the current state of the node. The graph neural network may update weights for the second node in a backward pass.

Abstract: A method of providing a personalized advertisement campaign includes receiving from a financial institution anonymized customer data associated with a plurality of customers of the financial institution, creating key lifestyle indicators, which describe customer attributes, from the anonymized customer data, delivering online a pre-advertisement to at least one selected customer of the plurality of customers, receiving a prospective unique customer identification code from the financial institution when at least one prospective customer accepts the pre-advertisement, matching the prospective unique customer identification code to at least one prospective customer of the plurality of customers, and delivering a financial application associated with the pre-advertisement to the at least one prospective customer with the matched prospective unique customer identification code.

Abstract: A system includes a crowdsourcing request circuit that configures parameter(s) of a crowdsourcing request related to obtaining information on a condition of a collateral for a loan, a crowdsourcing publishing circuit that publishes the crowdsourcing request to a group of information suppliers, and a crowdsourcing communications circuit that collects and processes response(s) from the group of information suppliers, and provides a reward to at least one of the group of information suppliers in response to a successful information supply event.

Abstract: The disclosed embodiments provide a system that verifies user access to accounts. One example method involves: receiving a request to access a feature of a first account; obtaining, from a data repository, one or more transactions of a first account; obtaining, from the data repository, one or more transactions of a second account; matching at least one of the one or more transactions of the first account to at least one of the one or more transactions from the second account; generating a first verification of ownership of the first account by a user based on the matching at least one of the one or more transactions of the first account to the at least one of the one or more transactions from the second account; and enabling the user to access the feature of the first account based on the first verification of ownership.

Abstract: A method of providing a personalized advertisement campaign purpose includes: receiving from a financial institution anonymized customer data associated with a plurality of customers of the financial institution and a prospective unique customer identification code associated with the plurality of customers of the financial institution; creating key lifestyle indicators, which describe customer attributes, from the anonymized customer data; receiving from the financial institution an authenticated unique customer identification code that is matched to authenticated data from at least one prospective customer of the plurality of customers of the financial institution; matching the prospective unique customer identification code to the authenticated unique customer identification code; matching the authenticated unique customer identification code to at least one key lifestyle indicators of the plurality of customers; and delivering a financial application form associated with the matched key lifestyle indicato

Abstract: The present disclosure relates to systems and methods for generating real-time quotes using machine learning algorithms. The system may include a processor in communication with a client device, and a storage medium storing instructions that, when executed, cause the processor to perform operations including: receiving an image of a vehicle from the client device, extracting one or more features from the image, based on the extracted features and using a machine learning algorithm, identifying one or more attributes of the vehicle, based on the identified attributes of the vehicle, determining a make and a model of the vehicle, obtaining comparison information based at least in part on the determined make and model, estimating a quote for the vehicle based on the comparison information; and transmitting the estimated quote for display on the client device.

Abstract: An information display system includes a computing system that is configured to implement a user interface, access a first database storing a plurality of loan workout rules, receive loan and borrower data regarding an existing loan, and determine a plurality of loan workout options based on the plurality of loan workout rules and the received loan and borrower data. The plurality of loan workout options are displayed on the user interface.

Abstract: By intercepting a natural language communication of a protected party, the communication is monitored, wherein the protected party is a human being. Within the monitored communication using a natural language processing engine, a natural language interaction between the protected party and a second party is detected. To determine an interaction pattern, the natural language interaction is analyzed. The interaction pattern includes data derived from the monitored communication, metadata of the protected party, and metadata of the second party. Using the interaction pattern and an interaction behavior model, an adverse result of the natural language interaction is predicted, wherein the adverse result comprises an economic loss to the protected party. By notifying the protected party, the predicted adverse result is intercepted.

Abstract: Systems and methods for assessing a credit exposure risk are provided. The methods include collecting credit facility data from at least one credit lender server device; determining, based on the credit facility data, at least one feature vector that is associated with at least one credit borrower device; applying at least one escalation rule to the feature vector; determining whether the at least one feature vector satisfies the applied escalation rule; and when the at least one feature vector is determined as not satisfying the applied escalation rule, performing an escalation action with respect to an entity associated with the credit borrower device.

Abstract: Systems, methods, and other embodiments for ML-Based automated below-the-line threshold tuning include, in one embodiment, training an ML model to predict probabilities that an event is fraudulent on a set of events (i) sampled from a set of historic events labeled by an alerting engine as either above-the-line events or below-the-line events on either side of a threshold line indicating that an event is suspicious, and (ii) confirmed to be either fraudulent or not fraudulent; determining that the alerting engine should be tuned based on differences between probability values predicted for the events by the trained machine learning model and the labels applied to the events; generating a tuned threshold value for the threshold line based at least in part on the probability values predicted by the machine learning model; and tuning the alerting engine by replacing a threshold value with the tuned threshold value to adjust the threshold line.

Abstract: Disclosed herein is a digital lending platform with integrated product, pricing, and eligibility. The digital lending platform includes, in some embodiments, one or more server hosts supporting an application stack of the digital lending platform. The application stack includes a loan-product database, a pricing algorithm, and an eligibility rules engine. The loan-product database includes each loan product of a number of loan products offered through the digital lending platform. The pricing algorithm is configured to determine a price for each loan product of the number of loan products. The eligibility rules engine includes eligibility rules for each loan product of the number of loan products. Also disclosed herein is a computer-implemented method of the digital lending platform with the integrated product, pricing, and eligibility.

Abstract: A controller for making initiating actions in a building management system (BMS) is shown. The controller includes a processing circuit configured to receive location data relating to the building occupant located at a first location outside of a building. The processing circuit is configured to, in response to determining the first location is within a first distance range of the building, provide control signals to a first subsystem of the BMS. The processing circuit is configured to receive location data relating to the building occupant located at a second location outside of the building. The processing circuit is configured to, in response to determining that the second location is within a second distance range of the building, provide control signals to a second subsystem of the BMS.

Abstract: A method of providing a loan credit to a customer before the customer requests the loan comprises obtaining, by a server, personal information for a customer by a credit broker application executing on the server, executing, on the server, a plurality of lender approval models using the personal information for the customer as input to each lender approval model, where each lender approval model is stored on the computer system in a byte code format as part of a private blockchain system, generating, by the server, a plurality of loan, evaluating, by a credit broker application executing on the server, the plurality of loan approvals based on a credit broker rule set, selecting, by the credit broker application, one of the loan approvals by the credit broker application, and presenting information to the customer comprising the terms of the selected loan approval by the credit broker application.

Abstract: A system and method for providing a corporate “co-signor” for potential purchasers of an automobile who do not meet captive lender or standard bank approval guidelines. The corporate co-signor does not sign or execute loan documents alongside the purchaser in a manner similar to co-signors in the prior art, but instead guarantees the loans that are underwritten using a “cosignloan” product implemented in agreement with a captive lender. The loan is based on a payment-to-income (PTI) basis, supported by the security provided by the corporate co-signor. The dealer will then be able to use the “cosignloan” product parameters to provide appropriate new, used, or certified pre-owned vehicles to the customer/purchaser. The corporate co-signor receives an administration fee for each loan. The administration fee, in one embodiment, is sent to a reserve account by the captive lender from the dealer booking proceeds.

Abstract: A device may receive application questions for an individual applying for credit with an organization. The device may broadcast the application questions to additional devices that have access to a distributed ledger for sharing credit worthiness information to cause at least one of the additional devices to generate an application response to the application questions and to process the application response using a smart contract. The device may receive one or more application responses that have been encrypted. Each of the application responses may include particular credit worthiness information relating to the individual. The device may decrypt the application responses. The device may determine a credit worthiness score for the individual using the application responses. The device may perform one or more actions that allow the device or another device associated with the organization to use the credit worthiness score to determine whether to approve the individual for credit.

Abstract: Systems and methods are provided for routing transactions from ATMs. In one embodiment, a method is provided that includes receiving a unique identifier that corresponds to a transaction requested by a user. In certain implementations, the unique identifier may be presented to the user by a third party separate from a provider of the ATM. The method may further include routing the unique identifier to an application programming interface affiliated with a provider of the ATM to confirm the transaction's validity. In certain implementations, the method may further comprise implementing the transaction and updating a settlement account to reflect the transaction.

Abstract: Techniques described herein are directed to lending products with different repayment mechanisms. In an example, indication(s) of purchase(s) made using a payment instrument associated with a first lending product can be associated with a first data structure, wherein the first data structure is associated with a balance determined based at least in part on the indication(s). Based at least in part on determining that the balance exceeds a predetermined threshold, a portion of the balance can be associated with a second data structure associated with a second lending product, wherein the first lending product and the second lending product are independently associated with different repayment mechanisms. The portion of the balance can therefore be repaid via a repayment mechanism associated with the second lending product.

Abstract: The Advantage2U® system is an on-line system that increases the buying power of customers, enables customers to pay down a vehicle loan more quickly than the standard payments for the loan term would allow, and enables customers with negative equity in a vehicle loan to more quickly reach a position of positive equity. The Advantage2U system accomplishes this by collecting weekly payments from customers, instead of monthly payments from the customers. Since vehicle loans require monthly payments, the Advantage2U system collects one quarter of the total monthly payment per week. However, since this results in the customer paying one quarter of the monthly payment for 52 weeks in a given year, instead of the customer making 12 monthly payments, the customer has effectively made 13 monthly payments in a given year, and the extra amounts paid are directly applied to the principal of the loan.

Abstract: A system and method for automated blockchain custody service for managing a set of custodial assets includes a blockchain service circuit structured to interpret a plurality of access control features corresponding to parties associated with a secured loan; a data collection circuit structured to receive first collateral data from at least one sensor associated with the collateral used to secure the loan; receive second collateral data regarding an environment of the collateral from an IoT circuit; and associate the first collateral data and second collateral data with a unique identifier associated with the item of collateral, wherein the blockchain service circuit is structured to store the unique identifier and associated collateral data as blockchain data; a smart contract circuit structured to create a smart lending contract; and a secure access control circuit structured to receive access control instructions from a lender of the loan via an access control interface.

Abstract: Disclosed are various embodiments for facilitating the cancellation or reversion of unauthorized operations. An operation initiated to be executed with respect to a user account is received from a computing device that has been authenticated. A notification of the operation is sent through at least one communication channel in response to receiving the operation. The notification facilitates a reply that causes the operation to be cancelled when the reply is sent within a first time period and causes the operation to be reverted when the reply is sent within a second time period after an expiration of the first time period.

Abstract: In some aspects, a computing system can detect synthetic identities based on attributes associated with online entities. The computing system can generate entity links between primary entity objects and a secondary entity object. The secondary entity object identifies a target consumer as a secondary entity for accounts identified by the primary entity objects. Attributes of the secondary entity object and attributes of the primary entity objects can be calculated and compared to determine an inconsistency between a combination of a name attribute value and an address attribute value of the secondary entity object as compared to the primary entity objects. A fraud warning indicating that the target consumer is likely to be a synthetic identity can be generated based on the inconsistency and other attributes of the target consumer, such as an inquiries attribute, a terminations attribute, a duration attribute, and so on.

Abstract: Systems and methods are provided to identify abnormal transaction activity by a participant that is inconsistent with current conditions. Historical participant and external data is identified. A recurrent neural network identifies patterns in the historical participant and external data. A new transaction by the participant is received. The new transaction is compared using the patterns to the historical participant and external data. An abnormality score is generated. An alert is generated if the abnormality score exceeds a threshold.