Abstract: A network assurance analytics (NAA) system and method is disclosed. The NAA can be part of a risk analytic for telecom (RAFT) program. The NAA system is configured to monitor telecommunications networks, detect errors or fraud in those telecommunications networks, and provide solutions to resolve the errors or reduce the fraud. Traffic of a telecommunications network is electronically monitored for at least one pattern that is indicative of a telecommunications anomaly. Based on a set of a set of telecommunications profiles stored in a database, a model score representing a value of the telecommunications anomaly is generated. A solution for the telecommunications network to reduce the model score associated with the telecommunications anomaly is then generated for execution on the telecommunications network.

Abstract: A method for dynamically updating a model is described. The method includes accessing a model that specifies expected characteristics for a transaction. The model includes variables associated with fraud. The method also includes receiving at least one value for each of the variables while monitoring transactions, and updating a distribution of values for each variable based on the received value. The received value is compared with the updated distribution to determine a deviation from a threshold value associated with a percentile of the updated distribution that is indicative of fraud.

Abstract: A system for creating an application comprises a user interface receiving user interaction that specifies visual properties and actions of a web application, and a code unit generating application data that describes the specified visual properties and actions of the web application.

Abstract: Data is received that characterizes one or more leads. Thereafter, it is determined, for each of the one or more leads, whether the lead is likely to be fraudulent and/or inaccurate using at least one predictive model. In some implementations, one or more of the utilized predictive models can be trained using a plurality of historical leads with known fraud or accuracy data. Data can be later provided that identifies and/or includes one or more of (i) those leads that are determined to be fraudulent and/or inaccurate and (ii) those leads that are determined not to be fraudulent and/or inaccurate. Related apparatus, systems, techniques and articles are also described.

Abstract: A system and method for building a predictive score without model training are disclosed. A set of predictive variables is defined based on raw data fields generated from raw data from one or more sources and domain knowledge. The raw data includes a historical set of transactions previously generated by one or more raw data sources. An scaled relative risk table to describe each predictive variable of the set of predictive variables is generated. The set of predictive variables is combined based on their associated relative risk tables to generate a predictive score for a future set of transactions.

Abstract: A computer-implemented method described for facilitating selection of an assortment of products to offer for sale. The method includes receiving transaction data representing characteristics of a plurality of commercial transactions including a first product and a second product. Product attribute data representing attributes for at least the two products are also received. Substitution demand data for the second product is estimated which represents demand for the second product given the first product is not available, the estimation being based on the transaction data and product attribute data.

Abstract: A system and method of revenue assurance for a service activity are presented. Multiple data feeds are received by a revenue assurance analytic system, where each data feed contains the same logical component of the service activity. The multiple data feeds are processed to detect revenue assurance issues in the service activity based on one or more common linking keys between disparate records related to the logical component.

Abstract: A decision model is applied to a set of current data from a mortgage portfolio to generate a first portfolio metric. The decision model is formed from a network of a plurality of predictive models that are trained on historical data derived from a plurality of mortgage account profiles for a plurality of mortgages within the mortgage portfolio. One or more of the predictive models is an action-based predictive model allowing modification of at least one attribute affecting performance of the mortgage portfolio. One or more of the attributes can be modified and a second portfolio metric can then be optimized, using the decision model, in light of at least one constraint (which can be user-defined). Related techniques, apparatus, systems, and articles are described.

Abstract: A method of modeling includes quantifying a co-operative strength value for a plurality of pairs of variables, and identifying a clique of at least three variables based on a graph of the co-operative strength values of a plurality of pairs of variables. The method also includes selecting a first pair of variables of the plurality of pairs of variables having a high co-operative strength value. A second clique may also be identified. A model of the first clique and a model of the second clique are made. The outputs of these models are combined to form a combined model which is used to make various decisions with respect to real time data.

Abstract: A computer-implemented method and system for automated entity identification for efficient profiling in an event probability prediction system. A first subset of entities belonging to one or more entity classes is defined. At least one historical profile is constructed for each entity in the subset of entities based on a set of possible outcomes of transaction behavior of each entity in the first subset of entities. Based on the historical profiles, a second subset of entities having transaction behavior associated with a transaction is selected, the transaction behavior being predictive of at least one targeted outcome from the set of possible outcomes. The first subset of entities is redefined with the second subset of entities.

Abstract: Techniques for visualization of decision logic are provided. In one aspect, the techniques can be implemented by providing a control within a graphical user interface to a user. The control can display a plurality of graphical user interface elements corresponding to linked nodes within a hierarchical structure. An input identifying a selected graphical user interface element within the control can be generated by a user. A selected node within the hierarchical structure can be identified based on the selected graphical user interface element. In response to a request from a user, modifying an appearance of a subset of the linked nodes within the hierarchical structure based on a desired visualization criteria, the linked nodes within the hierarchical structure and the selected node.

Abstract: An apparatus and method for developing financial risk decisions for a customer associated with a number of different financial services/channels are disclosed. A hierarchy of relationships among the financial services/channels is generated. Transactional behaviors of the customer related to each of the financial services/channels is summarized, using one or more analytical approaches executed on the hierarchy of relationships, to generate a customer level transactional behavior summary. A customer profile associated with the customer is generated which includes the transactional behavior summary and aggregated information on recent financial transactions associated with each of the financial services/channels. A score for a risk decision can be generated for one or more specific services/channels, based on the customer profile.

Abstract: A system and method for protecting identity fraud are disclosed. A system includes a detection subsystem to identify applications and/or accounts at risk of identity fraud, and a disposition subsystem to process data provided by the detection system and to determine whether identity fraud exists in the applications and/or accounts. According to an implementation, one or more neural network models are defined, each neural network model being configured to handle a class of cases related to the subject and a specific data configuration describing a case of the class. The one or more neural network models are run to generate data requests about the subject's identity, and the data requests are passed to a detection system that monitor transactions associated with the subject. Additional data associated with the transactions is requested until a threshold certainty is achieved or until available data or models are exhausted.

Abstract: A system and method for maintaining a pre-defined score distribution for financial transactions are disclosed. A number of memory spaces are defined for a memory structure. Transaction data for the financial transactions is received by the system. Each of the financial transactions is scored based on the transaction data to generate a batch of scores for the financial transactions. A score range is divided into k bins, where each of the k bins representing one memory space of the memory spaces of the memory structure. The batch of scores are aggregated by storing a count of each score of the batch of scores in an associated memory space of the plurality of memory spaces, and a percentile is computed for each score in the batch of scores based on a set of values associated with the count of each score. Each new financial transaction is scored to generate a new score, and a new percentile is assigned to the new score according to the set of values.

Abstract: Data characterizing a desired variable order and an unordered graph can be received so that all paths in the unordered graph can be enumerated and a first path in the unordered graph can be leveled according to the desired variable order in a first oblivious read once decision graph. For each additional path other than the first path, the additional path is leveled in the desired order, nodes of the additional path are added to the first oblivious read once decision graph, and a union operation is performed on the first oblivious read once decision graph to union graph roots on the first oblivious read once decision graph. Thereafter, generation of a second oblivious read once decision graph can be initiated after completing processing of the first path and each additional path. Related apparatus, systems, techniques and articles are also described.

Abstract: A request to compare strategies is received. The first strategy can be graphically represented by a first set of linked nodes arranged in a first form of decision logic. The second strategy can be graphically represented by a second set of linked nodes arranged in a second form of decision logic. The first set of linked nodes can be converted to a first modified set of linked nodes arranged in a third form of decision logic. The second set of linked nodes can be converted to a second modified set of linked nodes arranged in the third form of decision logic. A color-coded visual representation of the first modified set of linked nodes and the second modified set of linked nodes can be provided to a user. Related apparatus, techniques, and articles are also described.

Abstract: A system and method for building segmented scorecards for a population is presented. A model of the population is built using a model builder computer, and one or more variables used by the model builder to build the model is stored in a repository. A scorecard is generated for each segment of the population based on the model and using an adaptive random tree computer program. Next, the scorecard for each segment is enhanced using a integer non-linear programming computer program to determine optimal score weights associated with the variables used by the model builder to build the model, and to generate an enhanced segmented scorecard for the population.

Abstract: A system and method for drawing directed acyclic graphs is disclosed. In particular, an algorithm, as implemented in a method and system, to aesthetically layout directed acyclic graphs is presented. The algorithm includes methods to reduce the number of edge crossings and increase the number of straight edges in such drawings. The algorithm keeps short and straight edges wherever possible and gives preference to vertical edges. It also provides an edge-crossing reduction heuristic to refine the layout obtained after standard median heuristic layout, and further provides a method to focus on important paths in the graph through layout.

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: A system and method for automated variable creation for adaptive fraud analytics are disclosed. A data structure for creation of rules is generated. The data structure represents nodes and associations between nodes from inputs for fraud/non-fraud conditions, and is generated from fraud and non-fraud data collected in an adaptive modeling process from past transactions. All unique paths between nodes of the data structure are determined to define a rule for each path. Each rule is then converted to a binary indicator variable to generate a set of binary indicator variables, and one or more complex variables is derived from the set of binary indicator variables. The one or more binary indicator variables and one or more complex variables can be provided to an adaptive scoring engine to score new transactions or to predict future behaviors.