Abstract: Methods and systems described herein may implement blockchain cryptocurrency transactions in a variety of environments. An online transaction processor may provide operations for cryptocurrency conversions. The transaction processor may detect that a user is involved in a cryptocurrency transaction with another entity, which is requested to be processed using an amount of cryptocurrency and using an off-chain amount of the cryptocurrency. The transaction processor may determine that the entity does not have a digital wallet, node, or the like on a layer two network to receive and/or process the off-chain balance for the cryptocurrency. The transaction processor may then, after a risk assessment, determine that the user may access the amount of the cryptocurrency from an on-chain balance available to a digital wallet of the cryptocurrency. The transaction processor may make that on-chain amount available and may request repayment via the user's off-chain balance.

Abstract: A system and method for implementing a dynamic payments catalog is described. A set of processors that satisfy a set of requirements is identified. Required fields for each of the set of processors are further identified. Valid values for each of the required fields identified are determined. A dynamic payments catalog is built based on the identified required fields and valid values. Access to the dynamic payments catalog is then provided to clients.

Abstract: A method and system for detecting slow page load is provided. An example system comprises a page request detector, a time-out module, a time-out monitor, and a lightweight page requestor. The page request detector may be configured to detect a request for a web page. The time-out module may be configured to commence a time-out period in response to a request for a web page. The time-out module cooperates with the time-out monitor that may be configured to determine that rendering of a rich version of the requested web page has not commenced at an expiration of the time-out period. The lightweight page requestor may be configured to cause a lightweight version of the requested page to be provided to the client system when the time-out monitor determines that the rendering of a rich version of the requested web page has not commenced at an expiration of the time-out period.

Abstract: There are provided systems and methods for determining processing weights of rule variables for rule processing optimization. A service provider, such as an electronic transaction processor for digital transactions, may utilize different decision services that implement rules for decision-making of data including real-time data in production computing environments. Rules may correspond to coded statements that perform an automated decision-making service for the computing services and platforms of the service provider. When writing rules, different variables for data objects may be utilized, where each variable may perform a different operation and/or utilize a different operation for fetching and retrieving data used during rule processing. Each variable may therefore have a different data processing weights based on processing requirements of the data. Thus, optimization of rule authoring may be performed by mapping variables to other similar variables and showing a processing weight of each variable.

Abstract: Techniques are disclosed that relate to a computer system implementing an interactive voice response (IVR) transcoder. The computer system may receive voice input from an interactive voice response (IVR) system, or other channel. The computer system converts the received input to a request having a common format supported by an artificial intelligence (AI) core including one or more virtual agents. The computer system routes the request to the AI core operable to handle requests specified in the common format. The computer system receives, by the interface module, response data including data (e.g. text data) responsive to the second request. The computer system may implement a conversational artificial intelligence (CAI) platform. The computer system may receive text input from a chat-based input source. The computer system may route another request based on the text input to the AI core, the request being specified in the common text format.

Abstract: A system and application for purchasing one or more items via quick online transactions from a vendor system is provided. An electronic shopping page listing products for sale and corresponding buy selectors is provided on a user device that includes the quick transaction system. Upon user selection of a buy selector, the user's log on status and payment information are determined, and, if necessary, the user is prompted to log on to the quick transaction application and/or complete any missing user payment information if necessary. A single click or tap on the buy selector generates a completed purchase transaction without the need for a shopping cart or user checkout process. Methods and machine-readable medium for quick online transactions are also provided.

Abstract: In one embodiment, a method is illustrated as including defining a set of perspective objects capable of being placed onto a modified web page, monitoring parameters of a web page, the parameters including a number of times a current object is executed on the web page, using an Artificial Intelligence (AI) algorithm to determine a perspective object with a preferred Return On Investment (ROI), and selecting the perspective object to be placed onto the modified web page.

Abstract: There are provided systems and methods for an automated domain crawler and checkout simulator for proactive and real-time scam website detection. A service provider, such as an online transaction processor, may provide a domain crawler and checkout simulator that may be used to detect scam websites when registered and/or configured to utilize intermediary webpages of other domains to perpetrate fraud or scams on customers. The domain parser may detect new domain registrations and may parse through their corresponding websites to identify those that include checkout options or other processing flows that proceed through steps and use a service or feature of a service provider, including account usage for electronic transaction processing. The checkout simulator may then simulate a user's experience through the checkout to determine if domain redirections occur. If so, those redirections may be checked to identify usage of a merchant account having been flagged for scams.

Abstract: A system according to the present disclosure may include a processor, a centralized data warehouse, and a non-transitory computer readable medium storing thereon instructions that are executable by the processor to cause the system to perform operations. The operations may include receiving, from a user, identifying information, generating, based on the identifying information, a central profile for the user, generating, from the central profile, a first verification token configured to verify the user for a first service, and generating, from the central profile, a second verification token configured to verify the user for a second service. The first verification token and the second verification token are separately revokable and severable from the central profile, and neither the first verification token nor the second verification token comprise the identifying information of the user.

Abstract: Methods and systems are presented for providing a retrieval-augmented generation (RAG) framework that provides information associated with a particular domain to an artificial intelligence (AI). The RAG framework includes a query generation module that generates additional queries based on an original user query. A set of documents is retrieved from a corpus based on the user query and the additional queries. The RAG framework further includes an evaluation module for evaluating a relevancy of each retrieved document with respect to the original user query. Any documents determined to be irrelevant to the original user query may be eliminated, and the remaining documents along with the original user query are used to generate a prompt for the AI model, which in turn, generates a response to the user query.

Abstract: A method includes receiving a payment request that indicates a card identifier corresponding to a payment instrument to be used for payment. The method further includes determining that the card identifiers fails to satisfy at least one card activity criteria. Additionally, method includes subsequent to determining that no failed authorization attempts were performed for the card identifier within a previous time period, retrieving, from a database, a decline probability score associated with the card identifier. The method also includes based on the decline probability score, determining whether to transmit an authorization request for the card identifier prior to processing the payment request.

Abstract: Methods and systems are presented for classifying a digital image of a document using a machine learning model framework. The machine learning model framework is configured to provide a classification output based on a fusion of features corresponding to different modalities and extracted from the digital image. The machine learning model framework includes multiple encoders. Each encoder is configured to encode features corresponding to a distinct modality into a respective embedding. Different embeddings generated by the multiple encoders are fused together using one or more fusion techniques. The fused embedding is provided to a machine learning model for classifying the document.

Abstract: There are provided systems and methods for biometric authentication during voice data transfers. A user may initiate voice communications with a service provider endpoint that provides automated services to the user through the voice or audio communications, such as an interactive voice response (IVR) system where a user may navigate menus through audio commands. The user may by required to authenticate their identity during the phone call or other voice data transfer, which may be done by entering a biometric, such as a fingerprint. The biometric may be converted to biometric feature data and provided to one or more token service providers. The token service providers may provide one or more tokens for the biometric, which may be used as the authentication token. This token may then be transmitted to the IVR system through the user's endpoint using a dialer feature of the endpoint.

Abstract: A device may collect environmental information surrounding the device. Based on the collected environmental information, the device may automatically identify a potentially secured location that has lower security risk. When a potentially secured location is identified, the device may prompt the user to setup a security profile having reduced security requirement for the secured location. The device may store and associate the security profile with the secured location. The device may activate the security profile with reduced security requirement when the device is in the secured area. Further, the security profile may require that certain features of the device be disabled when the device is in the secured location.

Abstract: An indication is received that a first online platform has undergone/is undergoing a first electronic attack made by one or more actors engaged in online malicious actions with the first online platform. Responsive to the indication of the first electronic attack, one or more vulnerability characteristics of the first online platform are determined, where the vulnerability characteristics are associated with the first electronic attack. A plurality of other online platforms are analyzed to identify a second online platform that shares at least one of the vulnerability characteristics with the first online platform. Based on the determining and/or the analyzing, the second online platform is predicted to be a potential target for a second electronic attack having an attack vector in common with the first electronic attack that corresponds to the shared vulnerability characteristics. An action is performed to mitigate potential damage of the second electronic attack.

Abstract: Systems, computer-implemented methods, apparatus, and/or computer program products that can facilitate adaptable QR codes to launch customized experiences are provided. In various embodiments, a system can receive, from a client device, a quick response (QR) code, a client identifier, and location data associated with the client device. In various aspects, the system can identify, from a plurality of merchants, a first merchant that corresponds to the QR code, based on identifying that the first merchant corresponds to the location data. In various instances, the system can identify, from a plurality of client profiles, a first client profile that corresponds to the client identifier. In various cases, the system can identify a digital content based on the first merchant and the first client profile. In various aspects, the system can cause the digital content to be provided to the client device.

Abstract: Methods and systems are presented for configuring and training a machine learning model using transfer learning techniques that can transfer knowledge among multiple domains that do not share an identical feature set. Instead of using any feature set associated with a domain, a feature arrangement that combines all of the feature sets associated with the multiple domains in a particular organization for configuring and training the machine learning model. The feature arrangement includes a domain independent section and multiple domain-specific sections corresponding to the multiple domains. The domain independent section includes common features that are common across the multiple domains. Each of the domain-specific sections includes a feature set associated with the corresponding domain. The machine learning model that is configured in this manner can be trained to learn knowledge across the multiple domains and subsequently perform tasks for the multiple domains.

Abstract: Different communication and software protocols may be used by different blockchain networks. Cross-chain communication is provided via a software bridge configured to enable specific operations. An event request may be sent from a first blockchain network to a second blockchain network. The event request may be processed using a first protocol of the first network to provide a first output. An offer of equivalent processing provided by the second network may be verified by: processing the event request using a second protocol of the second network to provide a second output, and confirming that the second output matches the offer of equivalent processing. A processing equivalence of the event request may be established between the first network and the second network based on the first output of the event request processed using the first protocol and the second output of the event request processed using the second protocol.

Abstract: There are provided systems and methods for a guided web crawler for automated identification and verification of webpage resources. A service provider, such as an online transaction processor, may provide a guided web crawler and/or resources for such crawler for execution by computing devices of users. Users may load different pluggable modules to the guided web crawler, which are associated with specific web crawling tasks. Web crawling tasks may correspond to identification and verification of webpage resources on a webpage, such as a location, placement, use of, and/or number of appearances of the resource. The web crawler may use code from the pluggable module being executed to parse and/or crawl webpage data for a webpage and identify requested resources. Thereafter, the guided web crawler may automate resources to use, display, and/or interact with the identified and verified resource.

Abstract: There are provided systems and methods for correlating messages from asynchronous message queues using polling with exponential backoff and jitter. A service provider, such as an electronic transaction processor for digital transactions, may provide computing services to users, which may be used to engage in interactions with other users and entities including for electronic transaction processing. When utilizing these transaction processing services, merchant locations may utilize payment terminals, such as card and NFC readers, as well as point-of-sale devices, each of which may independently send transaction messages to the service provider. To correlate these messages from different queues, the messages may be stored when received in an intermediary storage independently and the other storage polled at intervals with exponential backoff to identify corresponding messages and data. Further, jitter may be introduced to the polling process to stagger polling events for different messages.