Abstract: Methods and systems for fault tolerant token based transactions are described. A user may perform a transaction with a mobile device. The mobile device may be in an offline mode or may be lacking a network connection to servers or cloud devices of a mobile payment system. The transaction may be processed through a transaction device, which may aid in the sending and receiving of transaction data while the mobile device is in the offline mode. The transaction device may communicate with the server or cloud device and the server or cloud device may process the transaction and communicate with the transaction device, which may forward data from the server or cloud device to the mobile device.

Abstract: A system and/or method may be provided to authenticate a user. An example method of authenticating a user includes receiving, by a merchant application, a user request to complete a transaction using a payment service provider. The method also includes in response to receiving the user request to complete the transaction, retrieving, by the merchant application, a browser cookie stored on a user device and associated with one or more user interactions with a browser included in the user device and the payment service provider. The method further includes in response to receiving the user request to complete the transaction, launching, by the merchant application, an instance of the browser that reads the browser cookie and authenticates the user based on the browser cookie.

Abstract: Methods and systems are presented for providing a framework for dynamically managing computer resources in processing transactions by selectively applying one or more techniques to improve the computer resource usage efficiency of processing different transactions. When a request for processing a first transaction is received, an estimated frequency of future transactions that are related to the first transaction is predicted. Based on the estimated frequency of future transactions, one or more actions that improves the computer resource usage efficiency for processing the first transaction are applied. The action may include suspending the processing of the first transaction and subsequently performing a batch process including the first transaction and a second transaction related to the first transaction. The action may include storing data associated with the processing of the first transaction in a cache memory for use in the subsequent processing of a second transaction.

Abstract: A system may perform operations including, for a given seed file, obtaining a first graph query to extract a first set of feature values from a first dataset, extracting, based on a feature calculation time, a sub-graph from the first dataset, obtaining, based on a second logic, a second graph query to extract a second set of feature values from a second dataset, and calculating a parity between the first set of feature values and second set of feature values. The operations may also include obtaining the events from a first data store, the events being filtered based on the given seed file, replaying the events backwards and extracting a third set of feature values, determining whether any of the second set of feature values do not match the second set of feature values, and updating the second set of feature values based on third set of feature values.

Abstract: Some embodiments may provide a method comprising receiving, from a remote machine, entity-identifying data and form identifying data, the form identifying data to identify a sequence of one or more electronic forms, the sequence including a target electronic form having a form element, determining an entity identifier, based on the entity-identifying data, accessing, from a data store, an entity attribute value based on the entity identifier, and transmitting, to the remote machine, form-filling instructions operable to cause a machine to automatically associate an entity attribute value with the form element.

Abstract: Methods and systems are presented for providing a computer platform that manages the impacts of government regulations on existing software processes of an online service provider. A regulation document is obtained from a government agency. The regulation document is processed, and legal obligations relevant to an online service provider are extracted from the regulation document. An ensemble machine learning model is used to recommend, for each of the legal obligations, software controls that can be implemented within one or more software processes of the online service provider to mitigate a risk of the legal obligations. The ensemble machine learning model may include an attribute-based model and a text-based model. An explainable visual interface is provided to present the recommended software controls and context that indicates to a user how the software controls are determined for the legal obligations.

Abstract: Techniques are disclosed for generating an altered version of an original version of media using a generative model. A system detects, at a computing device, a trigger event indicating a user of the computing device has requested to view media at a user interface of the computing device. In response to detecting the trigger event, the system: retrieves, an original version of the media from a backend server and identifies, using an object detection model, a bounding region of content within the original version, generates, using a generative model, an altered version of the media based on the bounding region, and transmits to the computing device, the altered version for display at the computing device in place of the original version, where the generative model generates the altered version of the media based on historical transaction information and user information of the user of the computing device.

Abstract: Methods and systems are presented for providing an artificial intelligence (AI)-based conversation system for facilitating a conversation with users and processing transactions for the users. The AI-based conversation system includes an AI model coupled with different backend modules. Based on an utterance submitted by a user during a chat session, the AI model is configured to generate instructions for a backend module to perform a transaction for the user based on a prompt template. The AI model also communicates the instructions to the backend module using a protocol specified in the prompt template. Upon receiving an output from the backend module, the AI model is configured to generate content for the chat session based on the output, and provide the content to the user.

Abstract: Techniques are disclosed for generating multiple different types of new features from a network graph and training a machine learning model using the newly generated features. A server system generates, from electronic communications, a network graph that includes nodes and edges. The server captures snapshots of the network graph that include nodes and edges existing at different time intervals. The system generates, for nodes included in respective snapshots, different types of features that include a neighbor convolution feature for a given node in a given snapshot by compressing node behavior features for neighbor nodes of the given node that are one hop away from the given node within the given snapshot of the network graph. The system trains, using the plurality of different types of features, a machine learning model usable to predict whether unlabeled nodes in the network graph are anomalous.

Abstract: Techniques are disclosed relating to speculatively processing transactions. A transaction processing system may receive an indication of a trigger event associated with an electronic transaction not yet initiated by a client computing device. In some embodiments, in response to the indication of the trigger event and prior to receiving an indication of the electronic transaction being initiated, the computer system begins speculative processing of the electronic transaction. In some embodiments, the speculative processing includes identifying the client computing device based on device authentication information received from the client device, determining a user account based on the identifier client computing device, retrieving account information for the determined account, and storing the retrieved account information.

Abstract: Methods and systems are presented for performing comprehensive and accurate matching of user accounts with one or more known entities based on image-linking graphs. Images related to each known entity are retrieved from one or more online sources. Faces are extracted from the images. Based on attributes of the faces in the images, an image-linking graph is generated for the entity. When a user account is determined to be a potential match for the entity based on text-based attributes, an image associated with the account may be obtained. If the image matches with any one of the faces in the image-linking graph, an action is performed to the user account based on a position of the matched face in the image-linking graph.

Abstract: Systems and techniques for facilitating implicit curriculum learning are provided. These allow for improved machine learning systems that can automatically execute curriculum learning without drawbacks such as pre-sorting data into different epochs which may have varying degrees of difficulty (e.g. easiest first, then harder epochs). Applicant's techniques can be executed more efficiently by automatically iterating over a data set, which need not be manually separated into different epochs. Thus, a system can access a neural network and a set of labeled data candidates. In various aspects, the system can perform a plurality of training epochs on the neural network based on the set of labeled data candidates.

Abstract: Embodiments provide systems, methods, processes, computer program code and means for using mobile devices to conduct transactions with value dispensing devices.

Abstract: A fraud detection model is used by a computer system to evaluate whether to grant a request to access a secure electronic resource. Before granting the request, the computer system evaluates the request using a multi-partite graph model generated using a plurality of previous requests. The multi-partite graph model includes at least a first set of nodes for sender accounts, a second set of nodes for recipient accounts, and a third set of nodes.

Abstract: Methods and systems for content distribution and management are presented. A transaction flow for conducting different stages of a transaction is determined in response to a request for the transaction from an application executable at a user device. The transaction flow includes a sequence of content pages to be displayed within a graphical user interface (GUI) of the application over the different stages of the transaction. The content associated with a tagged UI element of at least one content page is identified. The content is validated for the tagged UI element of the at least one content page, based on a software and hardware configuration of the user device. The validated content is provided via a network to the application at the user device to be displayable with the tagged UI element on the at least one content page of the transaction flow during a corresponding stage of the transaction.

Abstract: A method for offering at least one credit product by at least one credit issuer to a consumer at a point-of-sale between a merchant and the consumer. The method includes the steps of: providing a credit issuer data set including a plurality of data fields to a central database; initiating a transaction between the consumer and the merchant at the point-of-sale; offering, to the consumer at the point-of-sale, the at least one credit product; and presenting, to the consumer at the point-of-sale, at least one data field in the credit issuer data set. The at least one data field presented to the consumer is populated with data directed to the credit product, the credit issuer, or any combination thereof. An apparatus and system are also disclosed.

Abstract: Methods and systems are presented for facilitating computer software feature experimentation by using one or more graph analyses to partition users into different experimentation groups. A graph is generated to represent users of a service provider and relationships among the users. When a request to perform a software feature experiment on the users of the service provider, the graph is analyzed to determine an estimated spillover effect. The graph is then coarsened across multiple levels using a label propagation technique based on one or more coarsening parameters. After the graph has been coarsened, the graph is partitioned into multiple partitions based on one or more partitioning parameters. The coarsening parameters and/or the partitioning parameters may be determined based on the estimated spillover effect. A subset of users is selected for performing the software feature experiment based on the partitioning of the coarsened graph.

Abstract: System and methods for determining high-impact, non-informative features in datasets can include obtaining a first dataset including a first set of features and first set of tags, determining a second dataset including a second set of features and the first set of tags, the second set of features transformed from the first set of features, and each of the second set of features including a binary value, predicting, by a model, a third dataset including a third set of features and second set of tags based on the second dataset, comparing the third dataset to the second dataset to determine a correlation therebetween, based on the comparison, filtering at least one feature having missing feature values from the first dataset, and determining a training dataset with the remaining features in the first dataset, wherein the model being trained using the training dataset improves the outcome prediction accuracy of the model.