Abstract: A system and method for patient stratification include determining a first set of patient groups from patients in a patient similarity graph based on a similarity structure of the patient similarity graph. A second set of patient groups is identified based on expert domain knowledge associated with the patients. Patients in the first set and the second set are aligned using a processor to stratify patients.

Abstract: Electronic health records of a plurality of patients are received. A risk prediction model for a disease based on the electronic health records of the plurality of patients is created. An electronic health record of an original patient is received. A neighboring group of patients of the plurality of patients is identified, wherein the neighboring group of patients is two or more patients similar to the original patient. An ordering of the two or more patients of the neighboring group of patients is received, wherein the ordering of the two or more patients of the neighboring group of patients is based upon how similar each patient of the two or more patients is to the original patient. The risk prediction model is updated based on the ordering of the two or more patients of the neighboring group of patients.

Abstract: Electronic health records of a plurality of patients are received. A risk prediction model for a disease based on the electronic health records of the plurality of patients is created. An electronic health record of an original patient is received. A neighboring group of patients of the plurality of patients is identified, wherein the neighboring group of patients is two or more patients similar to the original patient. An ordering of the two or more patients of the neighboring group of patients is received, wherein the ordering of the two or more patients of the neighboring group of patients is based upon how similar each patient of the two or more patients is to the original patient. The risk prediction model is updated based on the ordering of the two or more patients of the neighboring group of patients.

Abstract: Electronic health records of a plurality of patients are received. A risk prediction model for a disease based on the electronic health records of the plurality of patients is created. An electronic health record of an original patient is received. A neighboring group of patients of the plurality of patients is identified, wherein the neighboring group of patients is two or more patients similar to the original patient. An ordering of the two or more patients of the neighboring group of patients is received, wherein the ordering of the two or more patients of the neighboring group of patients is based upon how similar each patient of the two or more patients is to the original patient. The risk prediction model is updated based on the ordering of the two or more patients of the neighboring group of patients.

Abstract: Provided is a mechanism to evaluate and predict credit ratings of corporations from a transaction perspective (i.e., on a transaction-by-transaction basis) by integrating real-time event and external information such as, for example, social media and news reports. In various embodiments, such a mechanism may be implemented via systems, methods and/or computer program products.

Abstract: Generating an electronic data model of a logical supply chain and regenerating the model based on changes to modelling parameters, to guide decision making. The data model is generated using known information about the supply chain. One or more decision scenarios are modelled based on a simulated loan request, and the data model is regenerated to consider the consequences. A recommendation is made based on pre-defined or user-defined criteria.

Abstract: Electronic health records of a plurality of patients are received. A risk prediction model for a disease based on the electronic health records of the plurality of patients is created. An electronic health record of an original patient is received. A neighboring group of patients of the plurality of patients is identified, wherein the neighboring group of patients is two or more patients similar to the original patient. An ordering of the two or more patients of the neighboring group of patients is received, wherein the ordering of the two or more patients of the neighboring group of patients is based upon how similar each patient of the two or more patients is to the original patient. The risk prediction model is updated based on the ordering of the two or more patients of the neighboring group of patients.

Abstract: A method of characterizing relationships among spatio-temporal events and a system to characterize the relationships are described. The method includes receiving information specifying the spatio-temporal events and associated categories from one or more sources. The method also includes building, using a processor, a directed acyclic graph (DAG) indicating a relationship among the categories for each of two or more space lag (SL) and time lag (TL) sets. Each of the two or more SL and TL sets defines a spatio-temporal boundary such that only the spatio-temporal events and the associated categories with (SL,TL)-neighborhoods inside the respective spatio-temporal boundary are considered in building the respective DAG. The respective (SL,TL)-neighborhood of each of the spatio-temporal events is a polygonal shape defined by the respective SL and the respective TL and the respective (SL,TL)-neighborhood of each of the categories is a union of the (SL,TL)-neighborhoods of the associated spatio-temporal events.

Abstract: A system, method and program product are provided for calculating a routing scheme for a set of correspondent banking (CB) transactions. The described system includes: a network modeling system that creates a model of a CB network for a set of banks based on existing relationships among and between the banks; and an optimization engine that generates a CB transaction routing scheme for an inputted set of CB transactions within the CB network, wherein the optimization engine provides an overall maximized economic benefit for executing each of the inputted set of CB transactions based on separately collected cost data, risk data and revenue data.

Abstract: A system, method and program product are provided for evaluating clients in a correspondent banking (CB) network with regard to CB product offerings. The disclosed system includes: a network modeling system that creates a model of a CB network, wherein the model is defined by a set of banks and a set of clients based on existing relationships among and between the banks and clients, and wherein the model is further defined with inputted risk data, expected return data, demand data, and cost data; and an evaluation engine that utilizes the model to generate a clientele evaluation for an inputted CB product offering within the CB network, wherein the evaluation engine determines a potential economic benefit of each client with regard to the inputted CB product offering.

Abstract: An aspect of an online learning system includes collecting data, via a computer processing device, from a plurality of data sources including multiple disparate detectors, the data including at least one of historical alarm data, failures, maintenance records, and environment observations. The data is stored in tables each corresponding to a subject of measurement. The online learning system also includes identifying common fields shared across the tables, merging at least a portion of the data across the tables having the common fields, and creating an integrated data model based on results of the merging.

Abstract: A system and method for patient stratification include determining a first set of patient groups from patients in a patient similarity graph based on a similarity structure of the patient similarity graph. A second set of patient groups is identified based on expert domain knowledge associated with the patients. Patients in the first set and the second set are aligned using a processor to stratify patients.

Abstract: Embodiments relate to analytics driven assessment of transactional risk daily limit (TRDL) exceptions. A transaction that includes a request to make a payment from an account associated with a customer is received and it is determined that processing the payment will result in exceeding a TRDL. Customer data including historical transaction data and customer profile data associated with the customer is accessed by a processor. Economic data from an external data source is accessed via a network from an external data source. A TRDL exception assessment model is applied, by the processor, to the transaction, the customer data, and the economic data to generate an approval recommendation for the request and a confidence level associated with the approval recommendation.

Abstract: Embodiments relate to analytics driven assessment of transactional risk daily limits (TRDLs). Customer data that includes historical transaction data and customer profile data associated with a customer is accessed by a processor. Economic data from an external data source is accessed via a network. A TRDL assessment model is applied, by a processor, to the customer data and the economic data to generate a TRDL for the customer.

Abstract: An aspect of customer selection processes includes classifying, by a computer processor, customers of an entity into groups based on commonly shared, predefined characteristics among the customers. For each of the groups: services rendered for corresponding customers are identified; for each of the services rendered, a risk relationship and a reward relationship between each of the corresponding customers and the service is determined; and for each of the services rendered, a score that defines a combination of the risk relationship and the reward relationship is calculated. For each of the services rendered by the entity, the corresponding score is applied to a candidate customer having a set of characteristics matching the characteristics of one of the groups, and the service is offered to the candidate customer as a function of the score.

Abstract: Embodiments relate to analytics-driven automated reconciliation of financial transactions. External information is correlated with a plurality of financial transaction reconciliation exceptions associated with a sequence of financial transactions over a period of time. A plurality of causal factors is identified from the external information associated with a pattern of the financial transaction reconciliation exceptions. A plurality of more recent financial transactions is monitored for the causal factors. An exception prediction alert is issued based on identifying the causal factors in the more recent financial transactions prior to detecting a new financial transaction reconciliation exception associated with the more recent financial transactions.

Abstract: Embodiments relate to analytics driven assessment of transactional risk daily limit (TRDL) exceptions. A transaction that includes a request to make a payment from an account associated with a customer is received and it is determined that processing the payment will result in exceeding a TRDL. Customer data including historical transaction data and customer profile data associated with the customer is accessed by a processor. Economic data from an external data source is accessed via a network from an external data source. A TRDL exception assessment model is applied, by the processor, to the transaction, the customer data, and the economic data to generate an approval recommendation for the request and a confidence level associated with the approval recommendation.

Abstract: An aspect of product recommendation processes includes classifying customers into groups based on commonly shared, predefined characteristics and common financial transaction activities conducted. For each service offered, the product recommendation processes include estimating a cost of recommendation of the service; and estimating, for each of the customers in a group, a transaction risk of providing the service.

Abstract: Embodiments relate to a transactional risk daily limit (TRDL) update alarm. Customer data including historical transaction data and customer profile data is accessed, along with economic data from an external data source. A TRDL alarm analytics model is applied to the customer data and the economic data to predict a number of transactions in a specified time period that are expected to exceed a TRDL. The TRDL alarm analytics model takes into account a payment transaction pattern associated with the customer. A threshold value is compared to the number of transactions in the specified time period that are expected to exceed the TRDL. An increase in the TRDL is requested to be applied at least during the specified time period based on the number of transactions in the specified time period that are expected to exceed the TRDL being greater than the threshold value.

Abstract: Embodiments relate to analytics driven assessment of transactional risk daily limits (TRDLs). Customer data that includes historical transaction data and customer profile data associated with a customer is accessed by a processor. Economic data from an external data source is accessed via a network. A TRDL assessment model is applied, by a processor, to the customer data and the economic data to generate a TRDL for the customer.