Abstract: There are provided systems and methods for a machine learning model and narrative generator for prohibited transaction detection and compliance. A service provider server, such as an electronic transaction processor, may generate a machine learning model using a supervised training technique, which may detect transactions that may be money laundering. The model may be iteratively trained by detecting flagged transactions and outputting those transactions to an agent for identification of false positives, which may be used to retrain the model. When outputting the flagged transactions, a narrative may be generated using an explainer graph and a machine learning prediction explainer that identifies the features of the transaction data that caused the transactions to be flagged. Further, once the model is trained additional transactions may be processed to determine whether the features of those transactions indicate prohibited behavior.

Abstract: Systems and methods are disclosed which may allow a user having a mobile device to check in to a location using a packet sequence that includes information for identifying the location transmitted by one or more Bluetooth® Low Energy (BLE) beacons at or near the location. The user may be able to store packet sequences for various locations that may allow the user to automatically check into these locations using the store packet sequences.

Abstract: Systems and method for splitting a bill offline include detecting one or more local devices using local wireless communications provided by a peer-to-peer communication module. At least one payer device of the one or more local devices is selected for apportioning a primary bill. An offline payment authorization is then received from each at least one payer device through local wireless communications provided by the peer-to-peer communication module. When an Internet connection is later detected, the system provider connects to the Internet and sends the offline payment authorization received from each at least one payer device to a payment provider device over the Internet. The payment provider device may then transfer funds from account(s) of the at least one payer device to the account of the system provider.

Abstract: There are provided systems and methods for an automated device data retrieval and analysis platform. A service provider server invokes an instance of an application in a remote processing environment using device data associated with the application and sends a control message that prompts the instance to send a request to a web server for a process script that invokes a process executable in the remote processing environment. The service provider server obtains traffic data a behavior of application data based on an interaction between the instance and the web server, and determines features of the application in a native state from the behavior of the application data. The server generates a data profile of the application that indicates the features in the native state and provides the data profile to a remote engine to detect potential malicious activity associated with the application from the detection operation.

Abstract: Methods and systems are presented for dynamically adjusting a risk classification of a risk source based on classifications of one or more other risk sources. The risk engine may first classify a first risk source as a first risk type based on an initial analysis of the first risk source. Subsequent to classifying the first risk source as the first risk type, the risk engine may determine that a second risk source is associated with a second risk type. Based on the determination that the second risk source is associated with the second risk type, the risk engine may re-classify the first risk source as the second risk type. The risk engine may then use the reclassification of the first risk source to improve network security of an online service provider.

Abstract: Systems and methods are provided for checking many users in to a location using a Bluetooth® low energy (BLE) beacon. The provided systems and methods may allow a BLE beacon to facilitate a check in with a remote server that processes check ins and then disconnect from the device used to check in. The device may be assigned a unique identifier that may be broadcast from the device during the check in so that the BLE beacon can quickly scan for the identifier and connect with the device based on the identifier to provide content and other information to the device.

Abstract: A payment device comprising of a housing, a slot for insertion of a user instrument located on a front surface of the housing, and wherein the housing includes a smart card interface integrated circuit that is configured to read an EMV chip located on the user instrument, and a universal serial bus (USB) type C male connector configured to be inserted into a female connector on a computing device, wherein the USB type C male connector is located on a back surface of the housing, and wherein a size of the USB type C male connector is configured so that when the USB type C male connector is inserted into the female connector on the computing device, the back surface of the housing is within a distance of three centimeters of a surface of the computing device.

Abstract: A system and method allows for a virtual object to be privately shared, exchanged, and/or viewed. The virtual object is associated with a real world location and may be viewed through a user device as part of a virtual reality and/or augmented reality world.

Abstract: Methods, systems, and computer program products for providing attribute-based card combinations for digital wallets are disclosed. A computer-implemented method may include associating a first asset with a digital wallet, associating a second asset with the digital wallet, receiving a request to determine a relationship between the first asset and the second asset in the digital wallet, determining the relationship between the first asset and the second asset in the digital wallet, creating the relationship between the first asset and the second asset in the digital wallet, notifying a user of the digital wallet about how a change to the first asset in the digital wallet is to affect the second asset in the digital wallet based on the relationship between the assets, and performing a transaction involving the digital wallet based on the relationship between the first asset and the second asset in the digital wallet.

Abstract: A system can merge text bounding boxes such as Optical Character Recognition (OCR) bounding boxes. A document can comprise a plurality of the text bounding boxes. Distance thresholds between text bounding boxes can be utilized for comparison against a distance threshold. Distance thresholds can vary depending on context information associated with the document. In response to a determination that text bounding boxes satisfy the distance threshold, the text bounding boxes can be assigned to a bounding box group.

Abstract: A method for phishing detection using uniform resource locators is discussed. The method includes accessing data from one or more of a monitored portion of website data and a monitored portion of emails, the data indicating a suspect Uniform Resource Locator (URL). The method includes assigning a rule score based on partial rule scores of each portion of the suspect URL, the rule score indicating a phishing potential based on URL rules. The method includes determining a uniqueness score of the suspect URL, the uniqueness score indicating a degree of uniqueness of the suspect URL from a plurality of known phishing URLs. The method also includes determining a URL phishing score based, at least in part, on the rules scores and the uniqueness score for the suspect URL.

Abstract: Techniques for an ultra-fact software compilation of source code are provided. A compiler receives software code and may divide it into code sections. A map of ordered nodes may be generated, such that each node in the map may include a code section and the order of the nodes indicates an execution order of the software code. Each code section may be compiled into an executable object in parallel and independently from other code sections. A binary executable may be generated by linking executable objects generated from the code sections. The methodology significantly differs from existing source code compilation techniques because conventional compilers build executable sequentially, whereas the embodiments divide the source code into multiple smaller code sections and compile them individually and in parallel. Compiling multiple code sections improves the compilations in order of magnitude from conventional techniques.

Abstract: Techniques are disclosed relating to detecting matching datasets using encode values. In various embodiments, a data monitoring system may perform encoding operations on a first dataset to generate a first encode value that corresponds to a particular one of one or more fields included in the first dataset. The data monitoring system may then determine whether the first dataset matches a previously analyzed dataset. For example, in some embodiments, data monitoring system may compare the first encode value to a previous encode value that corresponds to a second field of the previously analyzed dataset. Based on this comparison, the data monitoring system may generate an output value that is indicative of a similarity between the first encode value and the previous encode value. The data monitoring system may then determine whether the first dataset matches the previously analyzed dataset based on this output value.

Abstract: Machine learning based techniques are described for identifying sanctionable persons via monitoring a plurality of electronic content sources. This may allow for more rapid identification of prohibited or restricted transactions. A trained sentiment analysis classifier may classify a particular electronic content item as containing sanctionable conduct. An electronic textual analysis of the electronic content item may be performed to identify one or more individual names within the particular electronic content item. An indication as to whether the one or more individual names have been identified as individuals who may be subject to one or more sanction requirements that prohibit one or more online actions may be electronically stored in a data table. Various operations may be performed to block or otherwise restrict online accounts associated with the individual from performing online activities.

Abstract: Techniques are disclosed relating to machine learning techniques for performing user authentication based on the manner in which a user interacts with a client device, including the use of Siamese networks to detect unauthorized use of a device and/or account. In some embodiments, a server system may receive a request to authorize a transaction associated with a user account. The request may include transaction details and, separate from those transaction details, interaction data indicative of a manner in which a requesting user interacts with a client device during a user session. The server system may apply a machine learning model to the interaction data to create an encoding value that is based on the manner in when the requesting user interacts with the client device during the user session. The server system may then compare the encoding value to a reference encoding value and, based on the comparison, determine whether to authorize the transaction.

Abstract: Methods and systems are provided for facilitating shared mobile payments. According to an embodiment, a user can initiate a purchase using a mobile device. The mobile device can display a total price for the purchase. The first user can cooperate with one or more second users to share the cost of the purchase. The cooperation can be facilitated via the first and second users' mobile devices.

Abstract: Embedding of digital tokens within a digital video can occur cryptographically using a public key in some embodiments. The digital video may be altered in a variety of ways so that the video itself contains an integrated token that can represent various quantities. Audiovisual data can be altered to contain both a token and a perceptible user auditory or visual cue as to the presence of the encrypted digital token. A video with an embedded digital token may be sent to users on the Internet. A video recipient may be able to view the video and also take additional action or gain additional functionality from the digital token embedded in the video. Tokens can be embedded by altering video metadata so that the perceptible video content itself is not changed in some embodiments.

Abstract: Methods and systems for using cloned accounts to track attacks on user accounts are described. A user login attempt is detected for a user account from a client computing device. A determination is made that the user is not a legitimate user. The user is routed to a cloned user account. An analysis of the interaction between the user and the cloned user account is performed.

Abstract: A system, includes a non-transitory memory; and one or more hardware processors coupled to the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform operations comprising: transmitting a message from an application client to a service to request content from the service; ascertaining a failure of the service to provide the requested content; and in response to ascertaining the failure, applying data from the application client to an application in lieu of the requested content.

Abstract: Systems and methods for an account integration system include establishing, by a service provider device, a first session with a service provider account associated with a user. After determining that a second session between a user device and the third party account of the user is active, a first validation is caused to access third party account information associated with the second session. The third party account information and the service provider account information are concurrently displayed by a display interface of the service provider device. A transaction request for a transaction associated with the service provider account and the third party account of the user is received. Information is sent to cause a second validation of the transaction request by a provider of the third party account. In response to the second validation of the transaction request, the requested transaction is processed.