Abstract: A first request to conduct a transaction via a mobile application is received from a user of the mobile application. In response to the receiving of the first request, a first portion of a transaction flow is rendered on a graphical user interface of the mobile application. A determination is made that the mobile application is unable to render a second portion of the transaction flow. In response to the determining, a second request is sent to a server to provide details for the second portion of the transaction flow. After the sending, computer programming code is received. The computer programming code corresponds to the details of the second portion of the transaction flow. Based on the received computer programming code, the second portion of the transaction flow is rendered for the mobile application on the mobile device.

Abstract: Computer systems and methods for interfacing with a third party website, comprising determining that a webpage of the third party website is being output in an interface of a web browser, and in response, generating an interface element that at least partially overlaps the webpage in the interface. The interface element includes a user-selectable graphical trigger that, when selected, causes digital codes to be automatically input into a data entry interface identified in the webpage, thereby triggering the third party website to receive each of the digital codes and to return a respective response. Based on monitoring the respective response to each of the digital codes, a particular digital code is identified that causes a greatest change in a numerical value displayed in the webpage. The particular digital code is applied to obtain a resulting numerical value that is displayed in the webpage.

Abstract: Systems, methods, and computer-readable media disclosed herein relate to reducing computation and computing resources for certain blockchain related transactions. Specifically, software algorithms and architecture allow some transactions to avoid the need for recordation on a blockchain, which can be computationally expensive both for a requesting device and for various nodes on the blockchain. Thus, a computer system may receive indications of incoming transactions transferring digital assets to particular user accounts, and in response to requests from user accounts, the computer system facilitates one or more internal transactions between those accounts. In response to a request from a particular internal user account, the computer system may perform an outgoing transaction transferring one or more digital assets to an external user account from one or more internal user accounts.

Abstract: A system and method of performing a payment transaction in an augmented user experience displayed to a user of an augmented reality device. The system includes receiving a request for user authentication from a user, authenticating the user for performing payment transactions via a merchant application executed on the augmented reality device, receiving a request for payment to a merchant for an item offered for sale to the user in an augmented environment presented by the merchant application, processing payment in the payment amount between a payment account of the user and a merchant account, wherein the request for payment is performed without the user exiting the merchant application.

Abstract: A system, a medium, and a method are provided to split data paths among various devices in data communications system. In some instances, the server device receives a request from a remote device such as a website server or a checkout device, where the request indicates a user request to purchase one or more items. An account management component of the server device determines a user account associated with the user request and identifies a user device associated with the user account, such as the user's smartphone. An authentication component of the server device generates an electronic message that indicates that the user must authenticate the request such that the request may be processed and initiates a transmittal of the electronic message to the user's smartphone. The user may accept or authenticate the request to process the request.

Abstract: Techniques are disclosed relating to training a machine learning model to understand one or more rules without explicitly executing the rule. In some embodiments, a computer system generates synthetic samples for a trained machine learning model usable to make a classification decision, where the synthetic samples are generated from a rule and a set of existing samples. In some embodiments, the set of existing samples are selected based on exceeding a confidence threshold for the classification decision. In some embodiments, the computer system retrains the trained machine learning model using the synthetic samples.

Abstract: There are provided systems and methods for sentence level dialogue summaries using unsupervised machine learning for keyword selection and scoring. 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. When utilizing these services, memoranda may be generated that includes text from different online interactions. To provide summarization and searching of the memoranda, the service provider may implement an unsupervised machine learning framework that utilizes machine learning models to perform text preprocessing, keyword extraction, and keyword weighting when ranking and outputting relevant keywords. Once extracted and ranked, the keywords may be used to provide different insights to the memoranda. The keywords may be selected based on domains and tasks and the framework may be made pluggable and customizable for different systems and search operations.

Abstract: There are provided systems and methods for identifying transaction processing retry attempts based on machine learning models for transaction success. A service provider, such as an electronic transaction processor for digital transactions, may detect a failure of data processing for a transaction when processed with a separate data processing system, such as a card processing system for payment cards. In order to minimize cost and wasted resources for retrying transactions that are likely to further fail, a machine learning model may be implements that generates a predictive score for whether a failed transaction is likely to be successful if retried with the data processing system. The predictive score may be used to predict a probability of success, which may then be used with a cost function to determine a cost to retry the failed transaction and a cost to stop a retry of the failed transaction.

Abstract: Techniques are disclosed relating to automatically generating and analyzing database queries. In various embodiments, a database inquiry assistance system maintains a first machine learning model trained using query history data for a database and a second machine learning model using analysis history for the database. In an embodiment, the system receives from a user system a request for an inquiry into data stored in the database and identifies a sequence of queries for responding to the request, where identifying the sequence of queries includes applying the second machine learning model to the request. The system generates corresponding database query code for implementing one or more of the queries in the sequence of queries, where generating the corresponding database query code includes applying the first machine learning model to descriptors of one or more of the queries, and sends a plan identifying the sequence of queries to the user system.

Abstract: Systems/techniques for facilitating proxy objects for tracking processing of electronic coupon codes are provided. In various embodiments, a system can determine that a browser is performing a checkout on a frontend website. In various aspects, the system can cause the frontend website to instruct the web browser to transmit a validation request to a backend server, wherein the validation request identifies a coupon code and requests that the backend server determine whether the coupon code is applicable to the checkout. In various instances, the system can cause the web browser to append a proxy object to the validation request, wherein the proxy object fetches, during execution of the validation request by the backend server, an execution status of the validation request. In various cases, the system can receive, from the proxy object, the execution status and can initiate one or more electronic actions based on the execution status.

Abstract: In one embodiment, an intended recipient of money transmits a payment link created by the recipient to an intended sender of money, where the link contains a locator to a site of a payment provider, information about the recipient (e.g., phone number), and the amount of money to be sent. The link can be sent via email, text, IM, or other means. The sender then accesses the link, such as by clicking or tapping on the link, which launches a checkout or payment page for the sender on the payment provider site. The sender completes the payment page, and the payment is sent to the recipient by the payment provider.

Abstract: Systems and methods for smart cloud caching using edge computing and real-time customer journey insights are disclosed. In one embodiment, a system identifies a trend in communications received by a first edge cloud server, wherein each communication corresponds to a customer journey comprising user action steps performed in a client application. The system determines which user action steps cause API invocations to non-edge cloud servers and generates a sequence of API invocations in an order associated with the sequence of user action steps of the customer journey. The sequence of API invocations may be chained and/or bundled and stored in a cache for replication at edge cloud servers. The system may determine that the trend is pervasive in a geographical location based on satisfaction of a criteria, and replicate the cached sequence of API invocations at a cache of a second edge cloud server that services the geographical location.

Abstract: According to an aspect of an embodiment of the present disclosure, a method may include receiving a quick response (QR) code from a computing device, the QR code including a first entity identifier, and analyzing the QR code to determine a request to initiate a data transfer between a first entity associated with the first entity identifier and a second entity, and to determine one or more characteristics associated with the data transfer. The method may also include, based on the one or more characteristics, identifying a first QR code processing flow from multiple QR code processing flows to follow to process the data transfer, and verifying the first entity in the transaction based on the first entity identifier of the QR code and based on the first QR code processing flow. The method may also include processing the data transfer between the second entity and the first entity based on the first QR code processing flow.

Abstract: A method according to the present disclosure may include providing an embedded service in an application, in response to receiving an input via the embedded service, determining an applicable module of a plurality of modules based on a characteristic of at least one of the input or of the embedded service, processing the input via the applicable module, and controlling the application based on the processed input. Another method according to the present disclosure may include providing an embedded service in an application, training a monitoring model via federated learning based on data derived locally from the application, monitoring, via the trained monitoring model, a plurality of interactions with the embedded service, determining, by the trained monitoring model, that at least one of the plurality of interactions comprises an anomalous interaction, and in response to the determination, restricting further usage of the application.

Abstract: There are provided systems and methods for a machine learning model for probabilistic anomaly detection in streaming device data. A server obtains a plurality of features associated with a user interaction between a user device and the server. The server selects a combination of features from the plurality of features, where the combination of features comprises features having a variance of expected values that exceeds a threshold variance. The server selects a prediction engine to process the combination of features with a corresponding non-parametric statistical model of a plurality of non-parametric statistical models and to generate a prediction indicating a likelihood that the combination of features represents an anomaly corresponding to fraudulent activity. The server issues a remedial action to the user device through an application programming interface with a remedial action engine based on the prediction for applying the remedial action on the user interaction.

Abstract: Techniques are disclosed relating to monitoring network traffic of an embeddable browser displayed by an application executing on a mobile computing device. In some embodiments, a first layer of the application manipulates one or more user interface elements displayed in the embeddable browser. The first layer of the application then detects network requests made by one or more application programming interfaces (APIs) executed by the embeddable browser in response to the manipulating. In some embodiments, the first layer sends to a second layer of the application results of observing network requests. In some embodiments, the second layer of the application displays, in real-time, information corresponding to the results of observing network requests.

Abstract: Methods and systems are presented for providing a framework to securely integrate third-party logic into electronic transaction processing workflow. Third-party programming code that implements different third-party logic may be obtained and stored in a repository. A transaction processing request is received from a third-party server, and an instance of a transaction processing module is instantiated within an operating runtime environment to process a transaction according to a workflow. When the instance of the transaction processing module has reached an interruption point, the instance of the transaction processing module is suspended, and a third-party programming code is executed within an isolated runtime environment. The third-party programming code is configured to provide an output value based on attributes of the transaction. The instance of the transaction processing module then determines whether to authorize or deny the transaction based in part on the output value.

Abstract: A search engine determines a number of pages to present to a user based on one or more of a variety of factors. The search engine may send the search results to a client machine, which may present a subset of the results along with a pagination control in a scrollable interface. The pagination control may present the number of pages determined by the search engine. The search engine may also determine a number of search results to present prior to the presentation of non-scrollable user interface (UI) elements based on the same or different factors. After the amount of scrolling exceeds a threshold, a non-scrollable UI element may be displayed. Additional thresholds may exist, such that additional non-scrollable UI elements are added as the user continues to scroll.

Abstract: Methods and systems are presented for authenticating web content. A request to authenticate web content is received from a user device. A first document object model (DOM) tree representing elements of the web content within a hierarchical structure is accessed. A hash value for each node of the first DOM tree is calculated based on the corresponding element of the web content represented by that node. A second DOM tree associated with a host of the web content is retrieved from a database. The second DOM tree represents predefined elements of the web content. The hash value calculated for each node of the first DOM tree is compared with a hash value associated with a corresponding node of the second DOM tree to determine whether the first DOM tree matches the second DOM tree. The web content is authenticated when the first DOM tree matches the second DOM tree.

Abstract: Systems and methods for mobile application integration are described. These may include receiving a payment request a mobile application, sending a payment application detection request, receiving a detection response, and sending a customized user interface to the mobile device. The customized user interfaces are determined by whether an associated payment application is present on the mobile device and whether the mobile device is authenticated with the payment processing platform. These techniques can allow for a better user experience when interacting with the payment processing platform.