Method and system for implementing behavior isolating prediction model

• US 10,346,873 B1
• Filed: 06/22/2016
• Issued: 07/09/2019
• Est. Priority Date: 05/10/2012
• Status: Active Grant

• Current Assignee: JP Morgan Chase Bank, N.A. (JP Morgan Chase & Co)
• Original Assignee: JP Morgan Chase Bank, N.A. (JP Morgan Chase & Co)
• Inventors: Andrews, Burton Warren, Gemayel, Nader Michel, Pai, Dee, Sela, Rebecca Jeanette-Paul, Svenson, Joshua D., Weston, Arthur Eladio
• Primary Examiner(s): Kim, Eunhee
• Application Number:
  US15/189,455
• Time in Patent Office: 1,112 Days
• Field of Search: 703 2, 707603, 707737, 707803, 707805
• CPC Class Codes: G06F 16/287 Visualization; Browsing
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0251 Targeted advertisements

Abstract

According to an embodiment of the present invention, a computer implemented method and system for isolating variables in a behavior prediction model comprises: identifying a plurality of groups comprising a first group of variables and a second group of variables; building a model, using a computer processor, for capturing an effect of the first group of variables in predicting behavior for customers; building a subsequent stage of the model, using a computer processor, on a second group of variables to neutralize the effect of the first group of variables; displaying results of the model wherein the results minimize the effect of the first group of variables in predicting behavior at a user interface; and identifying a response based on the results for a segment of the customers.

Claims

1. A computer implemented system for isolating variables in a behavior prediction model, the system comprising:

an electronic input that identifies a plurality of groups comprising a first group of variables and a second group of variables;

a modeling processor that builds a model for capturing an effect of the first group of variables in predicting behavior for customers and further builds a subsequent stage of the model on a second group of variables to neutralize the effect of the first group of variables by selectively isolating the effect of the first group of variables to remove an influence of the first group of variables on the model, wherein the modeling processor applies a multi-stage process to perform one or more additional sequences and iterations where each stage is combined to generate an overall prediction behavior;

an interactive user interface configured to display results of the model and the overall prediction behavior that facilitate behavior prediction responsive to the electronic input, the interactive user interface coupled to the electronic input and modeling processor; and

a processor that tailors and provides a marketing offer to a potential customer based on the results of the model and overall prediction behavior.

2. The system of claim 1, wherein the model predicts likelihood of attrition in a banking application.

3. The system of claim 1, wherein the first group of variables comprises demographic variables.

4. The system of claim 3, wherein the second group of variables comprises network strength variables or product relationship variables.

5. The system of claim 3, wherein the second group of variables comprises network strength variables and the plurality of groups comprises a third group of variables comprising product relationship variables.

6. The system of claim 1, wherein the results are combined with one or more results of one or more additional iterations of applying the model and viewing the combined results in a matrix format.

7. The system of claim 1, wherein the variables for one or more of the first group and the second group are defined by the user.

8. The system of claim 1, wherein the input module is further configured to define an order sequence for applying each group of the plurality of groups to the model.

9. The system of claim 1, wherein a user selects an algorithm for building the model.

10. A computer implemented method for isolating variables in a behavior prediction model, the method comprising the steps of:

identifying, via an electronic input, a plurality of groups comprising a first group of variables and a second group of variables;

building a model, using a modeling processor, for capturing an effect of the first group of variables in predicting behavior for customers;

building a subsequent stage of the model, using the modeling processor, on a second group of variables to neutralize the effect of the first group of variables by selectively isolating the effect of the first group of variables to remove an influence of the first group of variables on the model;

applying a multi-stage process to perform one or more additional sequences and iterations where each stage is combined to generate an overall prediction behavior;

displaying results of the model and the overall prediction behavior at an interactive user interface;

identifying a response based on the results for a segment of the customers;

tailoring a marketing offer to a potential customer based on the results of the model and overall prediction behavior; and

providing the marketing offer to the potential customer.

11. The method of claim 10, wherein the model predicts likelihood of attrition in a banking application.

12. The method of claim 10, wherein the first group of variables comprises demographic variables.

13. The method of claim 12, wherein the second group of variables comprises network strength variables or product relationship variables.

14. The method of claim 12, wherein the second group of variables comprises network strength variables and the plurality of groups comprises a third group of variables comprising product relationship variables.

15. The method of claim 10, further comprising the step of:

combining the results with one or more results of one or more additional iterations of applying the model and viewing the combined results in a matrix format.

16. The method of claim 10, wherein the variables for one or more of the first group and the second group are defined by the user.

17. The method of claim 10, further comprising the step of:

defining an order sequence for applying each group of the plurality of groups to the model.

18. The method of claim 10, wherein a user selects an algorithm for building the model.