Systems and methods for selective use of risk models to predict financial risk

• US 7,668,776 B1
• Filed: 01/07/2002
• Issued: 02/23/2010
• Est. Priority Date: 01/07/2002
• Status: Expired due to Fees

• Current Assignee: First Data Corporation (Fiserv Incorporated)
• Original Assignee: First Data Corporation (Fiserv Incorporated)
• Inventors: Ahles, Daniel
• Primary Examiner(s): CAMPEN, KELLY SCAGGS
• Application Number:
  US10/041,765
• Time in Patent Office: 2,969 Days
• Field of Search: 705/35, 705/38, 705/44, 705/36.R, 705/42, 705/39, 705/16, 705/40, 235/379, 235/380
• US Class Current: 705/38
• CPC Class Codes: G06Q 20/108 Remote banking, e.g. home banking
• CPC Class Codes: G06Q 20/40 Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
• CPC Class Codes: G06Q 20/4016 involving fraud or risk level assessment in transaction processing
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

A risk system that performs a risk assessment of a financial transaction to obtain a first risk score, and based on first risk score performs post-score assessments by selectively utilizing various scoring models and databases. The post-score process re-assesses some of the borderline risks in order to capture beneficial transactions that may fail standard risk assessments that use a cutoff risk score to divide the transactions into either authorized or declined groups.

Claims

1. A computer-implemented method for processing financial transactions comprising:

selecting, via a processor, a first scoring model from a plurality of scoring models for determining a first risk score for a financial transaction; and

determining based at least in part on the first risk score, whether to determine a second risk score with a second scoring model different from the first scoring model, and wherein the second scoring model is selected from the plurality of scoring models, via a processor, based at least in part on a post-score rule.

2. The method of claim 1, wherein the financial transaction is a check transaction.

3. The method of claim 1, wherein determining the first risk score comprises obtaining data associated with the financial transaction and evaluating the data.

4. The method of claim 3, wherein obtaining the data comprises receiving a transaction authorization request from a merchant.

5. The method of claim 3, wherein evaluating the transaction comprises invoking a first scoring model from a plurality of scoring models, wherein the first scoring model calculates the first risk score.

6. The method of claim 1, wherein determining whether to determine the second risk score comprises evaluating the first risk score, wherein the second risk score is determined if the first risk score is lower than a predetermined first cutoff value, wherein the transaction is authorized otherwise.

7. The method of claim 6 further comprising:

determining the second risk score with the second scoring model; and

determining whether to authorize the transaction based at least in part on the second risk score.

8. The method of claim 7, wherein determining the second risk score comprises invoking the second scoring model from a plurality of scoring models, wherein the second scoring model calculates the second risk score.

9. The method of claim 7, wherein determining whether to authorize the transaction comprises evaluating the second risk score, wherein the transaction is authorized if the second risk score is higher than a predetermined second cutoff score.