Method and system for income estimation

• US 20070124235A1
• Filed: 11/29/2005
• Published: 05/31/2007
• Est. Priority Date: 11/29/2005
• Status: Abandoned Application

• Current Assignee: Citicorp Trust Bank, FSB (Citigroup Incorporated)
• Original Assignee: Citicorp Trust Bank, FSB (Citigroup Incorporated)
• Inventors: Chakraborty, Anindya, Bader, Frederick, Hui, Karen
• Application Number:
  US11/288,073
• Publication Number:
  US 20070124235A1
• Time in Patent Office: Days
• US Class Current: 705/38
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof
• CPC Class Codes: G06Q 40/06 Asset management; Financial planning or analysis

Abstract

An automated method and system estimates income of an individual loan applicant using credit bureau information and loan attributes. The method and system can use the credit bureau and loan information to calibrate an applicant'"'"'s debt-burden in cases where such information is not readily available or is unverifiable. The method and system can automatically verify income for applicants who choose to state their income in lieu of providing adequate documentation. Further, the method and system can be applicable to any retail lending business including, but not limited to, mortgage, auto loan, and credit cards, where credit bureau information forms a part of the data collection process and is available along with applicant'"'"'s information.

Claims

1. An automated computer-implemented method for estimating income, the method comprising the steps of:

collecting an applicant'"'"'s information;

saving the applicant'"'"'s information in a record;

compiling a database comprising records of other applicants;

preprocessing the records in the database;

selecting preliminary variables;

detecting potential outliers; and

creating a model;

wherein the model is used to estimate the income of the applicant.

2. The method of claim 1, wherein the applicant'"'"'s information comprises loan or credit information.

3. The method of claim 1, wherein the database comprises records of full documentation applicants.

4. The method of claim 1, wherein the database records comprise loan or credit information.

5. The method of claim 1, wherein the step of preprocessing the records in the database further comprises the step of defining a scope of the data in the database.

6. The method of claim 1, wherein the step of preprocessing the records in the database further comprises the step of handling missing values.

7. The method of claim 1, wherein the step of preprocessing the records in the database further comprises the step of recoding the data.

8. The method of claim 1, wherein the step of preprocessing the records in the database further comprises the step of performing variable transformation.

9. The method of claim 1, wherein the step of selecting preliminary variables is a process selected from the group consisting of multivariate regression, PLS regression with VIP scores, Genetic Algorithms, Neural Networks, CART, Regression Trees, and TreeNet.

10. The method of claim 1, wherein preliminary variables are selected from loan and credit information.

11. The method of claim 1, wherein the step of detecting potential outliers further comprises detecting typographical errors, uploading errors, or over-influential cases.

12. The method of claim 1, wherein the step of detecting potential outliers is a process selected from the group consisting of Euclidian distance, studentized deleted residuals, hat matrix, FFITS, Cook'"'"'s distance, DFBETAS, and Random Forest.

13. The method of claim 1, wherein the step of creating a model is a process selected from the group consisting of Global Linear Multivariate Regression, regression tree, MARS, and MART/Treenet.

14. The method of claim 1, further comprising the step of bootstrapping the model.

15. The method of claim 1, further comprising the step of evaluating performance of the model.