Higher risk score for identifying potential illegality in business-to-business relationships

• US 20030115133A1
• Filed: 12/13/2001
• Published: 06/19/2003
• Est. Priority Date: 12/13/2001
• Status: Abandoned Application

• Current Assignee: DUN & Bradstreet Incorporated (Dun & Bradstreet Corp.)
• Original Assignee: DUN & Bradstreet Incorporated (Dun & Bradstreet Corp.)
• Inventors: Bian, Jie
• Application Number:
  US10/021,253
• Publication Number:
  US 20030115133A1
• Time in Patent Office: Days
• US Class Current: 705/38
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof
• CPC Class Codes: G06Q 99/00 Subject matter not provided for in other groups of this subclass

Abstract

A system for providing a user with a higher risk score indicating the likelihood that a business under inquiry by the user is involved in questionable activity comprising a means for evaluating how closely the profile of the business under inquiry matches those of businesses already confirmed as higher risk wherein a neural network model is capable of capturing the way multiple variables (or factors or characteristics) inter-relate or recognizing patterns indicative of questionable activity;

Claims

1. A system for providing a user with a higher risk score indicating the likelihood that a business under inquiry by the user may be involved in questionable activity comprising:

means for evaluating how closely the profile of the business under inquiry matches those of businesses already confirmed as higher risk wherein a neural network model is capable of capturing the way multiple data elements inter-relate and thereby of recognizing patterns indicative of questionable activity, and means for transmitting a report of such risk to the user.

2. A system, as defined in claim 1, further comprising variables selected from the group of data elements:

(a) History Indicator

(b) Suits, Liens, Judgments

(c) UCC Filing Indicator

(d) SIC

(e) Name

(f) Company Age

(g) MSA

(h) Mail Drop

(i) Ownership of Facility

(j) Number of Employees

(k) Satisfactory Payment Experience

(l) Inquiry Spike

3. A system, as defined in claim 1, further comprising a network and, connected to the network, a programmed computer, a user interface, a means for gathering data elements concerning a plurality of businesses, a database having a record of the businesses appended with their respective data elements in the form of variables, or data elements, wherein the neural data elements, assigns weights to the elements to produce a weighted sum wherein higher weighted sums meaning a higher high risk score.

4. A system, as defined in claim 3, providing means for feeding the data elements into the neural network model.

5. A system, as defined in claim 4, including means for identifying the patterns of questionable activity.

6. A system, as defined in claim 5, including means for assigning weights to the data elements to produce a weighted sum.

7. A system, as defined in claim 6, providing means for calculating a weighted sum.

8. A system as defined in claim 1, wherein the evaluated business is given different scores based on how closely its patterns match those of confirmed risk businesses.

9. A method for providing a user with a higher risk score indicating the likelihood that a business under inquiry by the user is involved in questionable activity comprising steps of:

evaluating how closely the profile of the business under inquiry matches those of businesses already confirmed as higher risk wherein a neural network model is capable of capturing the way multiple data elements inter-relate and thereby of recognizing patterns indicative of questionable activity;

transmitting a report of the degree of risk to the user.

10. A method, as defined in claim 9, further comprising variables selected from the group of data elements:

(a) History Indicator

(b) Suits, Liens, Judgments

(c) UCC Filing Indicator

(d) SIC

(e) Name

(f) Company Age

(g) MSA

(h) Mail Drop

(i) Ownership of Facility

(j) Number of Employees

(k) Satisfactory Payment Experience

(l) Inquiry Spike

11. A method, as defined in claim 10, providing steps for feeding the data elements into the neural network model.

12. A method, as defined in claim 11, including steps for identifying the patterns of questionable activity.

13. A method, as defined in claim 12, including steps for assigning weights to the data elements to produce a weighted sum.

14. A method, as defined in claim 13, providing steps for calculating a weighted sum, on which the higher risk score is based.