Abstract: Systems and methods are provided for providing alerts to a user. The systems and methods may include a financial service provider including a memory device storing instructions. The financial service provider may also include at least one processor configured to execute the instructions to perform a plurality of operations. The operations may include receiving data relating to an activity of a user. The operations may also include identifying a merchant based at least on the received data. The operations may also include accessing historical fraud or disputes data associated with at least one of the user and the merchant. The operations may also include determining whether the received data triggers an alert. The operations may further include sending an alert message to a user device associated with the user when the processor determines that the received data triggers the alert.

Abstract: Provided herein are systems, methods and computer readable media for proving gift giving within a group. Consumers may register for a gift giving program, create a group and invite other consumers to participate. Group members may be randomly assigned to a group, or assigned to a group based on an invitation or indicated group. Relationships between gift givers and recipients within a group may be determined, such as in a randomized format. Gift givers may purchase a gift, such as a good or a promotion from a promotion and marketing service. The promotion and marketing service may assign the promotion to the recipient so that the recipient may redeem the promotion for a good, service, or experience. Promotions may be automatically purchased on behalf of a gift giver who fails to purchase the promotion by a gift-giving deadline.

Abstract: An online incentive network is optimized. Online incentive network data is accessed including data regarding sharing between users of the network from at least one database. Inputted parameters and network data are applied to one or more models for incentivized deal sharing to determine profitability of an incentivized sharing deal to offer to plurality of users via an online network for one or more products or services provided by a merchant. The incentivized sharing deal comprises a deal in which a user purchases a particular deal, and then when the user shares the particular deal with a threshold number of other users who also purchase the deal, the user receives an incentive. The parameters include a price of the deal; a proportion of the deal kept by the merchant or the online incentive network, and the number of incentivized users. An interface offers the incentivized sharing deal to users.

Abstract: An offer decay generation model determines, for a particular customer, a personalized optimal offer decay curve of an incentive corresponding to a product provided by an enterprise, where the offer decay curve defines a set of decreasing incentive values and respective time intervals during which each incentive value is valid. The offer decay generation model is trained on historical data indicative of customers, customer interactions, offered incentives, resulting outcomes of the incentives, and time intervals elapsing between incentives and resulting outcomes. As such, the optimized offer decay curve is structured to maximize a probability that the particular customer is motivated to accept the incentive offer, purchase a product, and/or further interact with the enterprise during the lifetime of the offer decay curve. The offer decay curve may unique to the individual customer, and may be further customized based on other parameters such as location, time/day/date, inventories, etc.

Abstract: A method includes: detecting, by a computing device, a new entry in one of plural databases; comparing, by the computing device, the new entry to watch entries defined in a watch database; determining, by the computing device, whether the new entry matches a watch entry in the watch database; creating, by the computing device, a new watch in the watch database when the new entry does not match any watch in the watch database; and updating, by the computing device, a watch in the watch database when the new entry matches the watch in the watch database.

Abstract: An improved system and process for machine-learning upgrade analysis and training thereof is provided herein. A request to analyze the time to upgrade a current system to a target system may be received. A change list having one or more changes for the target system may be read. Custom code for the current system may be compared to the change list to identify recommended changes to the custom code to upgrade the custom code to be compatible with the target system. The recommended changes may be classified into one or categories respectively via a trained first machine-learning algorithm. Time to upgrade the custom code for the respective classified changes may be estimated via a trained second machine-learning algorithm. The recommended changes, the classifications of the recommended changes, and the time estimates of the recommended changes may be provided.

Abstract: An approach is described for a method, product, and apparatus for a machine learning process using dynamic rearrangement of sparse data and corresponding weights. This approach includes a method, product, and apparatus for dynamically rearranging input data to move sparse data to a location such that computations on the sparse data might be avoided when executing a machine learning processing job. For example, sparse data within each row of the input matrix can be moved to the end of each corresponding row. When the input data is folded to fit the array, that sparse data might be at least partially contained within a fold that comprises only sparse data and possibly filler data. In such an event, computations on the fold are unnecessary and are avoided. In some embodiments, the approach includes dynamically rearranging a weight matrix to maintain a correspondence between the input data and the weights.

Abstract: Machine learning-based techniques for representing computing processes as vectors are provided. In one set of embodiments, a computer system can receive a name of a computing process and context information pertaining to the computing process. The computer system can further train a neural network based on the name and the context information, where the training results in determination of weight values for one or more hidden layers of the neural network. The computer system can then generate, based on the weight values, a vector representation of the computing process that encodes the context information and can perform one or more analyses using the vector representation.

Abstract: A server receives incoming data records comprising an ID value and respective user attributes corresponding to a user activity that originates at a user device. Characteristics of the activity and/or characteristics of the user device are considered in order to assign a probabilistic confidence value, which is in turn used to generate links from an incoming data record to other previously-received data records, and in so doing, generates a probabilistic link between one set of user attributes from the incoming data record and another set of user attributes from previously-received data records. A messaging campaign specification that describes target user attributes is used to identify a matching set of target audience member records. The determination of a match or not is based on the probabilistic confidence value and a threshold can be varied to extend audience reach. The identified set of target audience member records are transmitted over a network.

Abstract: Systems, data access management utilities, and methods generate links between local merchants and community programs, whereby the merchant may provide incentives to customers in relation to community programs. The implementations may track community programs, as well as online and offline customer transactions with merchants that make use of the incentive. Implementations may include as participants, customers, merchants, community organizations, intermediaries, and other groups or individuals. Participants may have participant identifiers, which may be linked to a payment source. Data may be collected about all participants, either expressly, or from offline or online transactions between merchants and customers utilizing a participant identifier, and the data may be stored in a data storage area.

Abstract: A method for distributing an electronic content item for consumption with advertisements is provided. In one embodiment, a content provider creates a license identifying one or more slots within an electronic content item at which advertisements are to be inserted. The license specifies one or more types of advertisements that are not permitted to be inserted into the slots, and also specifies criteria for dynamically selecting advertisements to insert into the one or more slots. The content provider securely associates the electronic license with the electronic content item and distributes the electronic content item and the electronic license to a third party for consumption or subsequent transfer to an end user.

Abstract: A method including receiving an input data set. The input data set can include one of a feature domain set or a kernel matrix. The method also can include constructing dense embeddings using: (i) Nyström approximations on the input data set when the input data set comprises the kernel matrix, and (ii) clustered Nyström approximations on the input data set when the input data set comprises the feature domain set. The method additionally can include performing representation learning on each of the dense embeddings using a multi-layer fully-connected network for each of the dense embeddings to generate latent representations corresponding to each of the dense embeddings. The method further can include applying a fusion layer to the latent representations corresponding to the dense embeddings to generate a combined representation. The method additionally can include performing classification on the combined representation. Other embodiments of related systems and methods are also disclosed.

Abstract: A method of generating and using a 2D barcode to provide an authenticated service subscriber with an adapted offer comprising monitoring and identifying, by a monitoring application associated with a first service provider, a social network for keywords related to a negative subscriber interaction with a second service provider; engaging a subscriber associated with the negative interaction by the first service provider; generating a one-time use 2D barcode associated with an offer and comprising embedded subscriber information; storing the barcode in a data store; sending the barcode to a mobile device; presenting and scanning the barcode; decoding the information by an offer application; authenticating the identity of the subscriber; adapting the offer based on the subscriber information; searching an inventory data store associated with a physical retail location of the first service provider; locating and presenting the adapted offer; and marking the barcode as expired in the barcode data store.

Abstract: A method for profit sharing is provided. The method includes deciding a first sharing rate according to a first event information and a first category information; obtaining a first sharing amount according to the first sharing rate and a first shared profit of the first category information; deciding a second sharing rate according to a second event information and a second category information; obtaining a second sharing amount according to the second sharing rate and a second shared profit of the second category information; deciding a total sharing amount by summing up the first sharing amount and the second sharing amount; and returning the total sharing amount in response to receiving a request from a user device.

Abstract: A computer-implemented method for computing node embeddings of a sparse graph that is an input of a sparse graph neural network is described. Each node embedding corresponds to a respective node of the sparse graph and represents feature information of the respective node and a plurality of neighboring nodes of the respective node.

Abstract: A method, system and computer program for providing a loyalty engine for automated cause marketing. The method includes a loyalty program system administrator linking merchants and charities to the loyalty system. Members register with the loyalty engine through loyalty system which is accessible via the Internet. Once the merchants and the charities are linked and the members are registered, by operation of the loyalty engine, the merchants can create a customized loyalty program defined by a plurality of merchant defined rules for administering their loyalty program. The merchant defined rules instruct the loyalty engine as to which charities should receive in-kind donations in connection with one or more transactions by a member that is associated to the loyalty program. Once a loyalty system defined time period or donation threshold has been achieved, the loyalty system releases the donation in-kind to the specific charity.

Abstract: A method of converting a data stored in a memory from a first format to a second format is disclosed. The method includes extending a number of bits in the data stored in a double data rate (DDR) memory by one bit to form an extended data. The method further includes determining whether the data stored in the DDR is signed or unsigned data. Moreover, responsive to determining that the data is signed, a sign value is added to the most significant bit of the extended data and the data is copied to lower order bits of the extended data. Responsive to determining that the data is unsigned, the data is copied to lower order bits of the extended data and the most significant bit is set to an unsigned value, e.g., zero. The extended data is stored in an on-chip memory (OCM) of a processing tile of a machine learning computer array.

Abstract: Provided herein are systems, methods and computer readable storage media for facilitating payments for consumer transactions and redemption of deal offerings. In providing such functionality, the system can be configured to, for example, receive payment for one or more products, determine a deal voucher's current value and cause the redemption of the deal voucher.

Abstract: Described are a system, method, and computer program product for applying deep learning analysis to predict and automatically respond to predicted changes in financial device primacy for a financial device holder. The method includes receiving transaction data representative of a plurality of transactions between the financial device holder and a merchant. The method also includes generating time series data based on the transaction data and generating a predictive model configured to: (i) receive an input of time-interval-based transaction data; and (ii) output a probability of primary financial device primacy change, the predictive model trained based on historic transaction data. The method further includes determining a probability of primary financial device primacy change for the financial device holder by applying the predictive model to the time series data. The method further includes, generating at least one communication to at least one issuer and/or the financial device holder.

Abstract: Disclosed are an electronic device and a method for controlling same. A method for controlling an electronic device according to the present disclosure comprises: a step of obtaining a program which shares data about an advertisement with another electronic device so as to verify the shared data; a step of, when an event for the advertisement occurs, generating first data including information about the event for the advertisement; a step of transmitting the generated first data to the other electronic device; a step of receiving second data including information about an event from the advertisement generated from the other electronic device; and a step of verifying the second data using the program.