Infrastructure and architecture for development and execution of predictive models

• US 9,195,671 B2
• Filed: 11/28/2012
• Issued: 11/24/2015
• Est. Priority Date: 04/09/2008
• Status: Active Grant

• Current Assignee: American Express Travel Related Services Company, Inc. (American Express Company)
• Original Assignee: American Express Travel Related Services Company, Inc. (American Express Company)
• Inventors: Murthy, Narasimha, Oralevich, Mickey S., Sacheti, Sandeep, Thomas, Deep
• Primary Examiner(s): Fleurantin, Jean B
• Application Number:
  US13/687,858
• Publication Number:
  US 20130091148A1
• Time in Patent Office: 1,091 Days
• Field of Search: 707/758, 707/802, 707/804, 707/999.102
• US Class Current: 1/1
• CPC Class Codes: G06F 16/13 File access structures, e.g. distributed indices arrangements of input from, or output to, record carriers G06F3/06
• CPC Class Codes: G06F 16/148 File search processing
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: H05K 999/99 dummy group

Abstract

A system that enables development and execution of predictive models comprises a centralized data management system, a data extraction tool a model validation tool and a model execution tool. In embodiments, a data management system includes a data management server that can be accessed via a web browser that stores data in the form of a flat file. An extraction tool extracts data. A model validation tool validates a model by scoring an analytical environment data set and a production environment data set. A model execution tool allows a user to select when and how often a model is scored.

Claims

1. A system comprising:

a processor configured for enabling execution of a plurality of models;

a tangible, non-transitory memory communicating with the processor, the tangible, non-transitory memory having instructions stored thereon that, in response to execution by the processor, cause the processor to perform operations comprising;

converting, by the processor using a data extraction tool and using a Structured Query Language (SQL) macro, SQL variables to Statistical Analysis System (SAS) variables in SAS datasets;

extracting, by the processor using the data extraction tool, data from SAS flat files based at least in part on contents of uploaded customer files respectively associated with customers,

wherein the data comprises customer variables,

wherein the data extraction tool includes a user interface, the SQL macro, privacy function, filtering function, and a model building function,

wherein the data is gathered by a data management system;

analyzing, by the processor, the customer variables in the customer files to determine trends in customer behavior;

determining, by the processor, the customer variables to use in the plurality of models,

wherein the customer variables are in the form of SAS datasets;

determining, by the processor, model logic based on the customer variables and the trends in customer behavior;

enabling, by the processor, creation of the plurality of models based on the model logic; and

scoring, by the processor and based on the plurality of models, the customers at a scoring frequency.

2. The system of claim 1, further comprising receiving, by the processor, the data from a plurality of data sources, wherein the plurality of data sources comprise a financial risk management system and at least one of:

an authorization system, a demographic system, and a spend/bill system.

3. The system of claim 1, further comprising:

storing, by the processor, a set of variables in a plurality of split files based upon a frequency of use of each variable in the plurality of models; and

reducing, based on the storing, a cycle time associated with a repeated execution of the plurality of models.

4. The system of claim 1, further comprising standardizing, by the processor, data stored in the SAS flat files.

5. The system of claim 1, further comprising validating, by the processor using a model validation tool, the plurality of models.

6. The system of claim 1, wherein the SAS flat file comprises a Statistical Analysis System (SAS) data set.

7. The system of claim 1, further comprising:

scoring, by the processor using a model validation tool, an analytical environment data set;

scoring, by the processor using the model validation tool, a production environment data set; and

comparing, by the processor using the model validation tool, scores generated by the analytical environment data set to scores generated by the production environment data set.

8. The system of claim 7, wherein results of the comparison between the scores generated by the analytical environment data set and the scores generated by the production environment are produced in a report.

9. The system of claim 1, further comprising validating, by the processor using a model validation tool, the plurality of models at least in part by using a pre-defined test case.

10. The system of claim 1, further comprising a model execution tool comprising an expiry date function that allows a user to specify how long the plurality of models will run.

11. The system of claim 1, wherein the scoring frequency further comprises an expiry date.

12. A method comprising:

converting, by a computer-based system configured for enabling execution of a plurality of models, Structured Query Language (SQL) variables to Statistical Analysis System (SAS) variables in SAS datasets, by using a data extraction tool and by using a SQL macro;

extracting, by the computer-based system using the data extraction tool, data from SAS flat files based at least in part on contents of uploaded customer files respectively associated with customers,

wherein the data comprises customer variables,

wherein the data extraction tool includes a user interface, the SQL macro, privacy function, filtering function, and a model building function,

wherein the data is gathered by a data management system;

analyzing, by the computer-based system, the customer variables in the customer files to determine trends in customer behavior;

determining, by the computer-based system, the customer variables to use in the plurality of models,

wherein the customer variables are in the form of SAS datasets;

determining, by the computer-based system, model logic based on the customer variables and the trends in customer behavior;

enabling, by the computer-based system, creation of the plurality of models based on the model logic; and

scoring, by the computer-based system and based on the plurality of models, the customers at a scoring frequency.

13. The method of claim 12, further comprising receiving, by the computer-based system, data from a plurality of data sources, wherein the plurality of data sources comprise a financial risk management system and at least one of:

an authorization system, a demographic system, and a spend/bill system.

14. The method of claim 12, further comprising:

storing, by the computer-based system, a set of variables in a plurality of split files based upon a frequency of use of each variable in the plurality of models; and

reducing, based on the storing, a cycle time associated with a repeated execution of the plurality of models.

15. The method of claim 12, further comprising standardizing, by the computer-based system, data stored in flat files.

16. An article of manufacture including a non-transitory, tangible computer readable storage medium having instructions stored thereon that, in response to execution by a computer-based system configured for enabling execution of a plurality of models, cause the computer-based system to perform operations comprising:

converting, by the computer-based system using a data extraction tool and using a Structured Query Language (SQL) macro, SQL variables to Statistical Analysis System (SAS) variables in SAS datasets;

extracting, by the computer-based system using the data extraction tool, data from SAS flat files based at least in part on contents of uploaded customer files respectively associated with customers,

wherein the data comprises customer variables,

wherein the data extraction tool includes a user interface, the SQL macro, privacy function, filtering function, and a model building function,

wherein the data is gathered by a data management system;

analyzing, by the computer-based system, the customer variables in the customer files to determine trends in customer behavior;

determining, by the computer-based system, the customer variables to use in the plurality of models,

wherein the customer variables are in the form of SAS datasets;

determining, by the computer-based system, model logic based on the customer variables and the trends in customer behavior;

enabling, by the computer-based system, creation of the plurality of models based on the model logic; and

scoring, by the computer-based system and based on the plurality of models, the customers at a scoring frequency.