Abstract: A computer-implemented fraud detection method and system for periodically identifying network associations in a consumer population at a national credit reporting agency and computing associated network level variables related to credit use and potential first party fraud for the consumer population. In response to receiving a request for a target account from among the consumer population the computer-implemented system retrieves credit report for the target account and computes tradeline or account level variables related to credit use and potential fraudulent behavior. A fraud score is calculated based on a combined evaluation of the network level variables and the tradeline or account level variables.

Abstract: A computer-implemented method for risk assessment and providing refinements to credit risk analysis based on a variety of information, including information voluntarily contributed by an applicant. The method may comprise performing a risk analysis based on a first set of information available in at least a first credit information data source and receiving a second set of information, in response to determining that the analysis provides a first result that is unfavorable to the applicant. The second set of information may be unavailable in the at least first credit information data source, and the second set of information may be retrievable from at least a secondary data source after the applicant's informed interaction with a computer-implemented interface configured to verify an authenticated approval by the applicant to provide access to information associated with at least one of the applicant's financial accounts.

Abstract: Data can be accessed from a plurality of disparate data sources from at least one database. A plurality of test models can be automatically built by a model building engine. Each test model can have predetermined predictive variables. A final set of predictive variables can be determined by a variable selector from the predetermined predictive variables in the plurality of test models by comparing the predictive power of the predictive variables across the plurality of test models. A master dataset can be generated from the disparate data sources. A master model can be built from the master dataset. The master model can combine the final set of predictive variables from the plurality of disparate data sources. The master model can characterize a quantitative estimate of the probability that an entity will display a defined behavior. Related apparatus, systems, techniques, and articles are also described.

Abstract: Data can be accessed from a plurality of disparate data sources from at least one database. A plurality of test models can be automatically built by a model building engine. Each test model can have predetermined predictive variables. A final set of predictive variables can be determined by a variable selector from the predetermined predictive variables in the plurality of test models by comparing the predictive power of the predictive variables across the plurality of test models. A master dataset can be generated from the disparate data sources. A master model can be built from the master dataset. The master model can combine the final set of predictive variables from the plurality of disparate data sources. The master model can characterize a quantitative estimate of the probability that an entity will display a defined behavior. Related apparatus, systems, techniques, and articles are also described.

Abstract: Data can be accessed from a plurality of disparate data sources from at least one database. A plurality of test models can be automatically built by a model building engine. Each test model can have predetermined predictive variables. A final set of predictive variables can be determined by a variable selector from the predetermined predictive variables in the plurality of test models by comparing the predictive power of the predictive variables across the plurality of test models. A master dataset can be generated from the disparate data sources. A master model can be built from the master dataset. The master model can combine the final set of predictive variables from the plurality of disparate data sources. The master model can characterize a quantitative estimate of the probability that an entity will display a defined behavior. Related apparatus, systems, techniques, and articles are also described.