Methods and systems for accessing multi-dimensional customer data
AssigneeGeneral Electric Capital Corporation
InventorsOumar Nabe, Michael A. Souery
Life of this patent
Estimating the term…
Abstract
Methods and systems for modeling customer data into a multi-dimensional structure for access to enable efficient customer targeting are described. The method includes the steps of compiling data from multiple sources to create a relational database, using tools to model data within the relational database, scoring the modeled data, integrating scores into a multi-dimensional structure and providing access to end users to the multi-dimensional structure.
Claims28
A method for providing to an end user, multi-dimensional customer profiles, allowing the end user to effectively manage customer targeting, said method comprising the steps of:
- compiling data from multiple sources to create a relational database;
- using tools to model the relational database and produce a first modeling result including at least one marketing model and at least one risk model for a customer, wherein the at least one marketing model includes a net present value/profitability model, a prospect pool model, a net conversion model, an attrition model, a response model, a revolver model, a balance transfer model, and a reactivation model, the tools include non-statistical tools including artificial intelligence;
- using the tools to compare the first modeling result to prior modeling results, and then select a modeling result to facilitate customer targeting;
- scoring the modeled database using the selected modeling result;
- integrating scores into a multi-dimensional structure;
- and
- providing access to end users to the multi-dimensional structure.
A system configured to provide to an end user, multi-dimensional customer profiles, allowing the end user to effectively manage customer targeting, said system comprising:
- at least one computer;
- a server configured to compile data from multiple sources to create a relational database, use tools including artificial intelligence to model data within the relational database and produce a first modeling result including at least one marketing model and at least one risk model, use tools to compare the first modeling result to prior modeling results and then select a modeling result to facilitate customer targeting, score the modeled data using the selected modeling results, integrate the scores into a multi-dimensional structure and provide access to the multi-dimensional structure, wherein the at least one risk model includes a payment behavior prediction model, a delinquency model, a bad debt model, a fraud detection model, a bankruptcy model, and a hit and run model;
- and
- a network connecting said computer to said server.
Dependencies are inferred from the claim text.