Abstract: A model governance framework uses a shared ledger on the back of a blockchain. The solution tracks various analytic tracking documents (ATDs) and associated assets, like requirements and sprints, through various stages of an ATD lifecycle. Data schema and data distributions are also tracked. The decision models, corresponding variables and execution codes are also tracked. Existing variables and execution codes are made available via a preexisting asset ATD for reuse. Various transactions provide mechanism for accessing and manipulating the various assets through a recorded ledger of events and approvals. A system provides tracking of the approvals and the approvers of all model assets that are touched by any participant, and further provides access control and security for multi-user access. An application layer provides graphical access to the various aspects of the blockchain.

Abstract: Computer-implemented systems and methods for selecting a first neural network model from a set of neural network models for a first dataset, the first neural network model having a set of predictor variables and a second dataset comprising a plurality of datapoints mapped into a multi-dimensional grid that defines one or more neighborhood data regions; applying the first neural network model on the first dataset to generate a model score for one or more datapoints in the second dataset, the model score representing an optimal fit of input predictor variables to a target variable for the set of variables of the first neural network model.

Abstract: A system and method for analyzing coverage, bias and model explanations in large dimensional modeling data includes discretizing three or more variables of a dataset to generate a discretized phase space represented as a grid of a plurality of cells, the dataset comprising a plurality of records, each record of the plurality of records having a value and a unique identifier (ID). A grid transformation is applied to each record in the dataset to assign each record to a cell of the plurality of cells of the grid according to the grid transformation. A grid index is generated to reference each cell using a discretized feature vector. A grid storage for storing the records assigned to each cell of the grid is then created. The grid storage using the ID of each record as a reference to each record and the discretized feature vector as a key to each cell.

Abstract: Computer-implemented systems and methods for selecting a first neural network model from a set of neural network models for a first dataset, the first neural network model having a set of predictor variables and a second dataset comprising a plurality of datapoints mapped into a multi-dimensional grid that defines one or more neighborhood data regions; applying the first neural network model on the first dataset to generate a model score for one or more datapoints in the second dataset, the model score representing an optimal fit of input predictor variables to a target variable for the set of variables of the first neural network model.

Abstract: Systems and methods that use a neural network architecture for extracting interpretable relationships among predictive input variables. This leads to neural network models that are interpretable and explainable. More importantly, these systems and methods lead to discovering new interpretable variables that are functions of predictive input variables, which in turn can be extracted as new features and utilized in other types of interpretable models, like scorecards (fraud score, etc.), but with higher predictive power than conventional systems and methods.

Abstract: A system and method for learning and associating reliability and confidence corresponding to a model's predictions by examining the support associated with datapoints in the variable phase space in terms of data coverage, and their impact on the weights distribution. The approach disclosed herein examines the impact of minor perturbations on a small fraction of the training exemplars in the variable phase space on the weights to understand whether the weights remain unperturbed or change significantly.

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: A system and method for learning and associating reliability and confidence corresponding to a model's predictions by examining the support associated with datapoints in the variable phase space in terms of data coverage, and their impact on the weights distribution. The approach disclosed herein examines the impact of minor perturbations on a small fraction of the training exemplars in the variable phase space on the weights to understand whether the weights remain unperturbed or change significantly.

Abstract: A model governance framework uses a shared ledger on the back of a blockchain. The solution tracks various analytic tracking documents (ATDs) and associated assets, like requirements and sprints, through various stages of an ATD lifecycle. Data schema and data distributions are also tracked. The decision models, corresponding variables and execution codes are also tracked. Existing variables and execution codes are made available via a preexisting asset ATD for reuse. Various transactions provide mechanism for accessing and manipulating the various assets through a recorded ledger of events and approvals. A system provides tracking of the approvals and the approvers of all model assets that are touched by any participant, and further provides access control and security for multi-user access. An application layer provides graphical access to the various aspects of the blockchain.

Abstract: A system and method for analyzing coverage, bias and model explanations in large dimensional modeling data includes discretizing three or more variables of a dataset to generate a discretized phase space represented as a grid of a plurality of cells, the dataset comprising a plurality of records, each record of the plurality of records having a value and a unique identifier (ID). A grid transformation is applied to each record in the dataset to assign each record to a cell of the plurality of cells of the grid according to the grid transformation. A grid index is generated to reference each cell using a discretized feature vector. A grid storage for storing the records assigned to each cell of the grid is then created. The grid storage using the ID of each record as a reference to each record and the discretized feature vector as a key to each cell.

Abstract: Systems and methods that use a neural network architecture for extracting interpretable relationships among predictive input variables. This leads to neural network models that are interpretable and explainable. More importantly, these systems and methods lead to discovering new interpretable variables that are functions of predictive input variables, which in turn can be extracted as new features and utilized in other types of interpretable models, like scorecards (fraud score, etc.), but with higher predictive power than conventional systems and methods.

Abstract: Profiles characterizing each of a plurality of consumers are received. Thereafter, each profile is associated with one of a plurality of customer segments (e.g., matched pairs, etc.). Thereafter, a coupon effectiveness index is determined for each of the plurality of consumers for an offering based on the associated customer segment. The coupon effectiveness indices model characterizes causal effects estimates determined using historical data of purchases of individuals having varying coupon treatments for the offering. Subsequently, provision of at least a portion of the determined coupon effectiveness indices is initiated. Related apparatus, systems, techniques and articles are also described.

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: The current subject matter describes a generation of a score based on an enhanced market basket analysis (eMBA). An eMBA model can receive historical data characterizing historical purchases of a plurality of products over a specified time-period. In response, the eMBA model can generate baskets, which can include data that is causal and predictive. The generated baskets can be provided as an input to a group generator. The group generator can then generate product groups and confidence values. The product groups and confidence values can be provided to a score generator. In run-time, the score generator can receive current product data, and in return, can use the product groups and confidence values to generate a score. The score can characterize a likelihood of a purchase of the product by a corresponding customer associated with the product group. Related methods, apparatuses, systems, techniques and articles are also described.

Abstract: A controlled and optimal provision of offers to customers on associated products is described. A three dimensional matrix characterizes product, customer, and time dimensions. Each product is associated with volume constraint(s). The three dimensional matrix is populated with scores. A score characterizes likelihood of a customer to purchase a corresponding product in an associated time period. First pairs of products and customers are randomly selected. The scores associated with the first pairs are changed to zero. Using volume constraints, an optimization is performed that excludes customers of the first pairs from a provision of best offers so that those customers are provided alternate offers. Based on the volume constraints, second pairs of products and customers are selected. The scores associated with the second pairs of products and customers are changed to one. Using volume constraints, optimization is performed such that customers of the second pairs are always provided best offers.

Abstract: Data is received that characterizes a plurality of procedures for a single event. Thereafter, one or more dynamically determined groups are associated with the plurality of procedures, the dynamically determined groups being generated from similarity metrics derived from a plurality of historical procedures for a plurality of historical events. A likelihood of the plurality of procedures being associated with the single event can then be determined based on the associated one or more dynamically determined groups. This determined likelihood can be used to determine whether the data is indicative of fraud. Related apparatus, systems, techniques and articles are also described.

Abstract: Various techniques are described that enable a smaller insurer (or an insurer with a less developed dataset) to be able to characterize whether certain healthcare insurance claim elements are potentially fraudulent or erroneous. Datasets from larger insurers (with well developed datasets) and/or datasets from a consortium of insurers can be leverage by the smaller insurer. Related techniques, apparatus, systems, and articles are also described.

Abstract: Various techniques are described that enable a smaller insurer (or an insurer with a less developed dataset) to be able to characterize whether certain healthcare insurance claim elements are potentially fraudulent or erroneous. Datasets from larger insurers (with well developed datasets) and/or datasets from a consortium of insurers can be leverage by the smaller insurer. Related techniques, apparatus, systems, and articles are also described.

Abstract: Data characterizing one or more healthcare insurance claims is received. Each claim comprises variables characterizing aspects of a healthcare service for which reimbursement is sought. The healthcare services being initiated by a single healthcare service provider for a single patient. Thereafter, score variables from the variables of the healthcare insurance claims are generated. Based on these score variables, it is determined whether a presence of one or more of the variables in more than one of the healthcare insurance claims is indicative of fraud or error based on levels of co-occurrence of the one or more pairs of variables in historical healthcare insurance claims being initiated by a single healthcare service provider. Subsequently, notification that the one or more of the healthcare insurance claims are indicative of fraud based on a positive determination is initiated (to allow, for example, a user to manually review the healthcare insurance claims, etc.).

Abstract: Data is received that characterizes a plurality of procedures for a single event. Thereafter, one or more dynamically determined groups are associated with the plurality of procedures, the dynamically determined groups being generated from similarity metrics derived from a plurality of historical procedures for a plurality of historical events. A likelihood of the plurality of procedures being associated with the single event can then be determined based on the associated one or more dynamically determined groups. This determined likelihood can be used to determine whether the data is indicative of fraud. Related apparatus, systems, techniques and articles are also described.