Abstract: There are provided systems and methods for a network of personalized devices determining data for shopping predictions. A personalized device may include processing components for determining purchase predictions for one or more items to purchase on behalf of a user. The purchase predictions may be based on personality traits and other information that may indicate interests of the user. The purchase predictions may also be based on purchase information for the item, including inventory of the item, price of the item, availability of the item to the user, or other factor. Once the purchase prediction is determined, the personalized device may generate a purchase request for the item from a merchant having the item at a physical merchant location accessible to the personalized device or a delivery device associated with the personalized device. The personalized device may retrieve and deliver the purchased item.

Abstract: Techniques are disclosed relating to the modification of user account functionality based on a physical state of a mobile device. For example, in some embodiments, a mobile device may detect one or more physical states associated with the device. The mobile device may compare the one or more physical states to a set of rules for a user account associated with a user, where a given one of the set of rules specifies one or more functionalities, of the user account, to modify in response to one or more of the rules being satisfied. Further, in response to the one or more physical states satisfying a first rule of the set of rules, the mobile device may send, to a server system associated with the user account, a request to modify one or more functionalities associated with the user account.

Abstract: Techniques are disclosed relating to determining characteristics associated with attempts to request access an online system. A security test that changes one or more parameters associated with accessing the online system may be implemented for a determined time interval. The parameters changed may include user interface parameters, security threshold parameters, and addresses of servlets in the online system. Access requests received during the security test may be compared to access requests received before and after the security test to determine characteristics of scripted access requests (e.g., automated attacks by one or more malicious users) and legitimate access requests to the online system. The present techniques enhance computer system security and can bolster network bandwidth by allowing malicious access requests to be more easily identified and filtered out.

Abstract: There are provided systems and methods for requesting payment for selected items or services using payment tokens. A first user, such as a requester for a transaction, may initiate a transaction with a merchant for at least one item or service. Upon checkout for the transaction, the first user may request that a second user complete payment for the transaction, such as a parent, spouse, or relative. A payment provider may generate a token for the transaction and instruct the merchant to hold the transaction for a period of time. The token may be communicated to the second user, a payer, for the transaction. The second user may then decide to authorize or decline payment for the transaction. The token may be kept valid for a period of time and the transaction may be cancelled with the merchant if the token is not paid for within the period.

Abstract: A bank account can be authenticated or confirmed by a user providing an account number and a debit card number. The payment provider then obtains user account information from the bank through a debit card network. The payment provider authenticates the account if the account numbers match. In another embodiment, authentication further requires a portion of a current bank balance in the account provided by the user to match the current balance received from the bank.

Abstract: Techniques are disclosed relating to the execution of queries in an online manner. For example, in some embodiments, a server system may include a distributed computing system that, in turn, includes a distributed storage system operable to store transaction data associated with a plurality of users, and a distributed computing engine operable to perform distributed processing jobs based on the transaction data. In various embodiments, the server system preemptively creates a compute session on the distributed computing engine, where the compute session provides access to various functionalities of the distributed computing engine. The distributed computing engine may then use these preemptively created compute sessions to execute queries (e.g., for end users of the server system) against the transaction data and return the results dataset to the requesting users in an online manner.

Abstract: Techniques are disclosed relating to determining whether document objects included in an image correspond to known document types. In some embodiments, a computing system maintains information specifying a set of known document types. In some embodiments, the computing system receives an image that includes objects. In some embodiments, the computing system analyzes, using a first neural network, the image to identify a document object and location information specifying a location of the document object within the image. In some embodiments, the computing system determines, using a second neural network, whether the document object within the image corresponds to a document type specified in the set of known document types, where the determining is performed based on the location information of the document object. In some embodiments, disclosed techniques may assist in automatically extracting information from documents, which in turn may advantageously decrease processing time for onboarding new customers.

Abstract: Methods and systems are presented for testing software applications in a production-like environment that simulates real-world failures of production environments. A production environment has production applications and databases configured to process user requests from users for conducting transactions with a service provider. A testing system provides an intermediate interface that enables a software application operating in the test environment to access at least one of a production application or a production database. The intermediate interface can be configured based on different failure configurations to simulate production component failures in the production environment. Failure injection and randomized failure modes can be employed, including for network-related failures (latency, dropped packets, connections, etc.) that might occur in the production environment.

Abstract: Anomalies in a data set may be difficult to detect when individual items are not gross outliers from a population average. Disclosed is an anomaly detector that includes neural networks such as an auto-encoder and a discriminator. The auto-encoder and the discriminator may be trained on a training set that does not include anomalies. During training, an auto-encoder generates an internal representation from the training set, and reconstructs the training set from the internal representation. The training continues until data loss in the reconstructed training set is below a configurable threshold. The discriminator may be trained until the internal representation is constrained to a multivariable unit normal. Once trained, the auto-encoder and discriminator identify anomalies in the evaluation set. The identified anomalies in an evaluation set may be linked to transaction, security breach or population trends, but broadly, disclosed techniques can be used to identify anomalies in any suitable population.

Abstract: Systems, methods, and computer program products for providing cloud-based application security are disclosed. For example, a server part of a cloud-based application may determine a plurality of security challenges for authorizing a request based on a plurality of security settings of a user account and one or more attributes of the request, issue a first-level authorization challenge and a second-level authorization challenge based on the determining, identify a plurality of available resources from the user account for the request, and responsive to successful completion of the first-level authorization challenge and the second-level authorization challenge, automatically apply two or more of the available resources from the user account to fulfill the request based on the one or more attributes of the request and a physical location associated with the request.

Abstract: There are provided systems and methods for an inline editing field for nested website settings. A computing device may be used to process a search query with a search engine and receive results. The search query may include a search for a particular website setting, such as a user profile, account, security, or preference setting that may allow a user to provide input and affect particular user or website data with the website. Determination of the requested website may be performed through a machine learning engine. The machine learning engine may identify the security setting nested in the website through multiple navigations, website flows, and navigations, and may extract processes and flows for use of the setting. An inline editing field may then allow for user input in a search interface that allows for editing the setting without navigation to the website and nested setting.

Abstract: A system includes an interface to receive a request associated with a third party at a financial service provider from a network-based device associated with a user. The request includes an identifier that identifies an offer. The system further includes a revenue share application configured to determine whether the transaction involves a plurality of third parties and to determine a payment share for each party of the plurality of third parties based on the transaction involving the plurality of third parties. A payment transfer module transfers the payment share from an account of the user to each account associated with each party of the plurality of third parties.

Abstract: Tracking and clawing back unspent transaction output (UTXO) tokens mechanism are disclosed for distributed ledger technology-based networks (DLTNs) operating a UTXO-based token transaction model (which can include blockchain networks). Some embodiments comprise receiving a request to transfer a UTXO token in a DLTN operating a UTXO-based token transaction model. Further, the embodiments can include determining that a clawback list includes the genesis token identifier and barred token identifiers of UTXO tokens barred from being transferred on the DLTN. In addition, the embodiments can include determining whether the clawback list includes any of the ancestral token identifiers of the UTXO token and generating an instruction regulating the transfer of the UTXO token in the DLTN based on the determining whether the clawback list includes any of the ancestral token identifiers. Such techniques improve the security and functionality of DLTNs such as a blockchain network.

Abstract: Systems and methods for message encryption include transmitting, to a first device through a first communication channel, a modification rule message including a modification rule. A first message is encrypted using a first key to generate an encrypted message. The encrypted message is modified based on the modification rule to generate a modified encrypted message. The modified encrypted message is transmitted to the first device through a second communication channel.

Abstract: A system is provided for voice activated remittances. The system may perform operations that include receiving at least one audio stream corresponding to a real-time voice communication between a first user and a second user and identifying, based on the at least one audio stream, a set of words. The operation may also include determining that the set of words indicates a desired payment transaction between the first user and the second user and determining a payment amount to be remitted from the first user to the second user. Further the operations may include causing the payment amount to be remitted from a first financial account corresponding to the first user to a second financial account corresponding to the second user.

Abstract: A system and method for securing application programming interface (API) requests using multi-party digital signatures. The method includes generating, by a first system, at least one first secret share of a plurality of secret shares based on an API secret, wherein the plurality of secret shares includes the at least one first secret share and at least one second secret share, wherein the at least one second secret share is generated by at least one second system; and signing, by the first system, an API request using the at least one first secret share, wherein the API request is further signed by the at least one second system using the at least one second secret share, wherein the API request is signed without revealing any of the at least one first secret share to the at least one second system and without revealing any of the at least one second secret share to the first system.

Abstract: Techniques are disclosed relating to processing database transactions that include application operations defined by different object relational mapping (ORM) libraries. A transaction router module executing on a computer system receives, from an application, a request for a first database transaction, where the first database transaction includes first and second application operations. The transaction router module then translates the first application operation to one or more first database operations using a first ORM library and the second application operation to one or more second database operations using a second ORM library. Then, the transaction router module determines one or more database connections for the one or more first database operations and the one or more second database operations. Such techniques may advantageously allow applications to switch between using different persistence frameworks and message broker frameworks without substantial adjustments to application code.

Abstract: Systems and methods for machine learning feature processing are disclosed. An example method includes: selecting a predefined number of machine-based transactions; identifying a first set of features based on the predefined number of machine-based transactions; and applying a machine learning feature selection algorithm to identify a second set of features. The second set of features is smaller than the first set of features, and the second set of features includes no more than a predefined number of features. The method also includes constructing a decision tree based on the second set of features, wherein the decision tree has a depth that is less than a predefined depth. The method optionally includes limiting the total number of features in the second set to no greater than the predefined number of features.

Abstract: Systems and methods are disclosed for detecting anomalies in text content of data objects even when a format of the data and/or data object is unknown. These may include receiving a first data object that corresponds to a first application service and that includes first text content. An anomaly classifier may be trained based on an artificial neural network by using a natural language processing algorithm on respective text content of at least a portion of each of a plurality of data objects corresponding to the first computing service. Each of the plurality of data objects may be labeled as belonging a category. The trained anomaly classifier may identify one or more text character sequences in the first text content of the first data object as anomalous and output identifying information indicating the one or more anomalous text character sequences in the first text content of the first data object.

Abstract: A system, computer-readable storage medium storing at least one program, and computer-implemented method for providing recommendations based on social network sharing activity. Sharing activity relating to the sharing of the content item on a social network by a first user is accessed. Consumption information related to the consumption of the content item. A correlation between the sharing activity and the consumption information is determined. A recommendation is then generated based on the correlation.