Predictive model development

Abstract

Models are generated using a variety of tools and features of a model generation platform. For example, in connection with a project in which a user generates a predictive model based on historical data about a system being modeled, the user is provided through a graphical user interface a structured sequence of model generation activities to be followed, the sequence including dimension reduction, model generation, model process validation, and model re-generation. In connection with a project in which a user generates a predictive model based on historical data about a system being modeled, and in which the project includes a series of user choice points and actions or parameter settings that govern the generation of the model based on rules, which direct the user to select and apply an optimal model.

1 . The method of  claim 8  in which
 the project includes a series of user choice points and actions or parameter settings that govern the generation of the model based on rules, and automatically stores information about the choice points and actions or rules.   
     
     
         2 - 6 . (canceled) 
     
     
         7 . The method of  claim 1  also including enabling the user to replicate information about the predictive model as it existed as of the making of any one of the choices. 
     
     
         8 . A machine-based method comprising
 in connection with a project in which a user generates a predictive model based on historical data about a system being modeled, providing to the user through a graphical user interface a structured sequence of model generation activities to be followed, the sequence including sample dataset generation, variable transformation, dimension reduction, model generation, model process validation, model re-generation, and list scoring.   
     
     
         9 . The method of  claim 8  in which the system comprises behavior of prospective or current customers of a vendor with respect to products or services offered by the vendor. 
     
     
         10 . The method of  claim 8  in which the predictive model predicts behavior of a prospective or current customer with respect to purchase of a product or service of a vendor. 
     
     
         11 . The method of  claim 8  in which the predictive model predicts behavior of a current customer with respect to retention of a current service or product of a vendor. 
     
     
         12 . The method of  claim 8  in which the predictive model predicts behavior of a current customer with respect to risk of asserting claims, loan payment or prepayment to a vendor. 
     
     
         13 . The method of  claim 8  in which the predictive model predicts behavior of a current customer with respect to usage of a current service or product of a vendor. 
     
     
         14 . The method of  claim 8  in which the user interface controls staging of the sequence of model generation activities. 
     
     
         15 . The method of  claim 8  in which the at least some of the activities comprise model design choices including rule parameter settings to be made by the user and at least some of the choices are constrained based on characteristics of types of the historical data. 
     
     
         16 . The method of  claim 8  in which the data types are represented by metadata associated with the data. 
     
     
         17 . The method of  claim 8  in which the sequence of activities includes subsequences and the user interface controls staging of the subsequences. 
     
     
         18 . The method of  claim 8  in which the sequence is selected to produce an optimal model subject to constraints of the project goals. 
     
     
         19 . The method of  claim 8  in which
 each of the model generation activities includes choices to be made by the user, and the method further includes   enabling the user to re-enter an earlier one of the model generation activities and to adjust a choice made included in that model generation activity, while continuing to impose the structured sequence on the model generation activities to be followed.   
     
     
         20 . The method of  claim 19  in which the at least one of the activities which the user re-enters includes adjustment of a model generation parameter and review of results produced by the adjusted parameters. 
     
     
         21 . The method of  claim 19  in which the re-entry is performed iteratively. 
     
     
         22 . The method of  claim 8  also including
 enabling the user to interact with a single integrated model generation platform to perform input processing of the historical data, generating of the model, and generating an output that identifies a selection, including rank by propensity, of prospect or current customer data based on scoring of the historical data using the model.   
     
     
         23 . The method of  claim 22  also including encrypting the output. 
     
     
         24 . The method of  claim 8  in which
 each of the model generation activities is indicated by an icon, the icons being connected by transitional graphical elements.   
     
     
         25 . The method of  claim 24  in which, at a given time, icons are displayed to indicate the status of one or more activities. 
     
     
         26 . The method of  claim 24  in which the transitional graphical elements are shown in one style for transitions that have been completed and in another style for transitions that are optional or are in process. 
     
     
         27 . The method of  claim 24  also including maintaining information about successive states and transitions of the model generation activities.