Abstract: A configuration package receives user-generated input that configures a decision service to generate decision data. The configuration package includes artifacts and the user-generated input selects the artifacts from an artifact library in a configuration database. A configured decision service is generated, where the generating includes receiving, by a decision service factory, the configuration package. Also, the decision service factory receives a decision template including configurable decision elements and non-configurable decision elements. Further, the decision service factory receives a user configuration specifying a parameter in the corresponding artifact. The artifact from the configuration package, the user configuration and the decision template are combined to generate the configured decision service. The configured decision service receives, from a client computer, input for each of the configurable decision elements.

Abstract: The current subject matter relates to generation of relevant real-time offers based on global positioning system (GPS) data of an individual. A mobile device of an individual can record the GPS data of the individual. The mobile device can be connected to a central system. The central system can receive the recorded GPS data. The central system can predict, by using a trained predictive model and based on transaction history of the individual and the GPS data, categories of likely purchases by the individual. The central system can generate or reproduce offers from merchants of the predicted categories that are located within a threshold distance from a current location of the individual. The central system can send the generated offers to the mobile device that can display the generated offers in real-time. Other applications can include improving relevance of batch offers and/or real-time offers based on a recent purchase trigger.

Abstract: This document presents multi-layered, self-calibrating analytics for detecting fraud in transaction data without substantial historical data. One or more variables from a set of variables are provided to each of a plurality of self-calibrating models that are implemented by one or more data processors, each of the one or more variables being generated from real-time production data related to the transaction data. The one or more variables are processed according to each of the plurality of self-calibrating models implemented by the one or more data processors to produce a self-calibrating model output for each of the plurality of self-calibrating models. The self-calibrating model output from each of the plurality of self-calibrating models is combined in an output model implemented by one or more data processors. Finally, a fraud score output for the real-time production data is generated from the self-calibrating model output.

Abstract: An automated way of learning archetypes which capture many aspects of entity behavior, and assigning entities to a mixture of archetypes, such that each entity is represented as a distribution across multiple archetypes. Given those representations in archetypes, anomalous behavior can be detected by finding misalignment with a plurality of entities archetype clustering within a hard segmentation. Extensions to sequence modeling are also discussed. Applications of this method include anti-money laundering (where the entities can be customers and accounts, as described extensively below), retail banking fraud detection, network security, and general anomaly detection.

Abstract: A system and method for a secure remote payments process and for generation of one-time only remote payment cards is presented. Use of the one-time payment (OTP) cards can use multi-factor authentication where one factor is a biometric technique. A process can include generating an OTP card number based on a first encryption algorithm, an expiry date, and a security code based on a second encryption algorithm. A purchase amount, and the OTP card information are decrypted by an issuer to approve payment for a remote payment, after which the OTP card is no longer valid.

Abstract: One or more datasets are received by a data wrangling module and wrangled into a form that is computationally actionable by a user. At least some data from the one or more datasets are enriched by one or more data enrichment modules to generate an enriched form of at least some data corresponding to the one or more datasets that is computationally actionable by the user. The one or more datasets and the enriched form of the at least some data are processed by a signal detection module to identify relationships, anomalies, and/or patterns within the one or more datasets.

Abstract: A problem of finding unknown associations between ‘concepts’ in a given text corpus is addressed. A new framework for computing and visualizing the association between concepts using the generic association measures and the public knowledge available in data sources such as Wikipedia. Indirect association analysis extends the utility of the proposed framework to a broader class of association mining applications including the interesting area of new hypothesis generation.

Abstract: Data characterizing an individual is received. Thereafter, one or more variables are extracted from the data so that, using a predictive model populated with the extracted variables, a likelihood of the individual adhering to a treatment regimen can be determined. The predictive model is trained on historical treatment regimen adherence data empirically derived from a plurality of subjects. Subsequently, data characterizing the determined likelihood of adherence can be promoted. Related apparatus, systems, techniques and articles are also described.

Abstract: A system and method for assessing the cybersecurity breach risk associated with a given organization is disclosed. The system and method assume no internal visibility into any organizational network. A taxonomy of possible data sources is defined and motivated. The system and method are both purely empirical and robust against common difficulties in scoring organizational networks, such as the raw number of network assets owned by the organization.

Abstract: Fraud detection is facilitated by developing account cluster membership rules and converting them to database queries via an examination of clusters of linked accounts abstracted from the customer database. The cluster membership rules are based upon certain observed data patterns associated with potentially fraudulent activity. In one embodiment, account clusters are grouped around behavior patterns exhibited by imposters. The system then identifies those clusters exhibiting a high probability of fraud and builds cluster membership rules for identifying subsequent accounts that match those rules. The rules are designed to define the parameters of the identified clusters. When the rules are deployed in a transaction blocking system, when a rule pertaining to an identified fraudulent cluster is triggered, the transaction blocking system blocks the transaction with respect to new users who enter the website.

Abstract: Systems and methods are provided for allowing a merchant to provide a consumer with a real-time, personalized offer to execute a consumer transaction in response to evaluating that consumer's credential information. The consumer provides the credential information while, or just before, the consumer selects items to purchase from the website. The credential information provided by the consumer can be a compilation of different information associated with the consumer and may take the form of a score. According to one embodiment of the present invention, a merchant receives credential information relating to a consumer, while the consumer is at that merchant's website. The merchant evaluates the credential information while the consumer remains at the website and makes a real-time personalized offer of goods, services or pricing based at least in part on that evaluation.

Abstract: The state of a system is determined in which data sets are generated that include a plurality of data instances representing states of one or more components of a computer system. The data instances generated by one or more data set sources that are configured to output a data instance in response to a trigger associated with the one or more components. The data instances are normalized by the application of one or more rules. The data instances from individual data set sources are separately collated to generate groups of time-specific collated data instances. State types may be assigned to each of the collated data instance groups. Distributions of state-types across the groups may be determined and a list of infrequent state-types may be generated based on the determined distributions of state-types across the groups.

Abstract: Computer implementation methods of processing transactions to determine the fraud risk of transactions incorporating card issuer bin and cardholder location associated with a multitude of customers. The artificial intelligence models developed with such information provide an output of likelihood of fraud for payment card transactions. Disclosed are the methods of utilizing aggregated payment card transaction data at the card issuer bin and card holder location level to improve fraud detection. The implementation of the method is demonstrated to have boosted the performance of the developed models in detection of fraudulent payment cards.

Abstract: A method for analyzing and implementing sentiments includes sorting data from the data stream into sorted data by using a corpus builder. The sorted data is then input into an opinion mining platform where selected content is obtained based on the identification of keywords present in the sorted data. A sentiment extraction program generates sentiment metrics based on analysis of the selected content. A rules extractor program determines, based on the sentiment metrics satisfying rules, if actions are to be performed by a business rules engine.

Abstract: A system and method of building a decision or prediction model used for analyzing and scoring behavioral transactions is disclosed. A customer dataset in a model development store is used to build an original model is subject to a data right usage withdrawal, the original model having coverage over the customer dataset extract, using data sampling, a portion of the customer dataset to generate a model surrogate dataset. The system and method discretize vectors present in both the model surrogate dataset and the customer dataset, and receive data representing the data right usage withdrawal from the customer dataset. The system and method determine a depletion of the model surrogate dataset according to the data right usage withdrawal, and compute an estimated mean time to coverage failure of the original model based on the depletion of the model surrogate dataset according to the data right usage withdrawal.

Abstract: A cloud-based decision management platform along with corresponding method, system, and a computer program product are disclosed. At least one component of at least one computing system is selected from a plurality of components of the computing system. The selected component is configured for execution during a runtime of the computing system. The configured component is executed during runtime. The components of the computing system are stored in a catalog module based on at least one characteristic that includes at least one of the following: analytics, decisioning, identity and access management, and optimization.

Abstract: The current subject matter describes a method and system of detecting frauds or anomalous behavior. The procedures include extracting characteristics from a dataset to generate words and documents, executing a topic model to obtain the respective probabilities of appearance of a document in each latent archetype, dividing the dataset into a plurality of subsets based upon the archetypes. The formed subsets are further utilized to estimate the quantiles and calculate scores using a self-calibrating outlier model. The score of each new transaction is determined based on a single archetype or based on the sum of weighted scores determined from all the archetypes and associated statistics. Such methods are superior to a simple self-calibration outlier model without an LDA archetype.

Abstract: A computing server can receive, from a computing device, an extensible markup language document and a location path pointing to an identifier uniquely identifying the extensible markup language document. The computing server can rearrange data within the extensible markup language document to generate a table including data arranged according to one or more location paths indicated by the extensible markup language document. Each location path of the one or more location paths can point to a storage location for data listed under the location path. The table can be specific to the identifier uniquely identifying the extensible markup language document. The computing server can store the table in a data store connected to the computing server. The computing server can retrieve, when required, the stored data from the data store within a time independent of a total number of XML documents in the data store.

Abstract: The subject matter disclosed herein provides methods, apparatus, systems, techniques, and articles for false positive reduction in abnormality detection models. A date and time of a first transaction by a transaction entity and associated with a transaction characteristic can be stored. Data representing subsequent transactions associated with the transaction characteristic can be stored. A history marker profile specific to the transaction characteristic and transaction entity can be generated and can include the transaction characteristic, the date and time of the first transaction, and maximum and mean abnormality scores. A date and time of a current transaction can be determined. A current abnormality score for the current transaction can be received. A tenure of the observed transaction characteristic can be computed.

Abstract: A testing framework associated with a decision metaphor model tool reads table profile files to generate requests for a test of a decision metaphor. The testing framework sends the requests for the test to a decision engine and receives responses for the requests for comparison against expected values and possible errors. The testing framework also outputs an output file that includes a result of the test, where the output file is formatted in a computer-displayable and user-readable graphical format.