System and method for assuring the integrity of data used to evaluate financial risk or exposure

• US 8,266,025 B1
• Filed: 08/08/2000
• Issued: 09/11/2012
• Est. Priority Date: 08/09/1999
• Status: Active Grant

• Current Assignee: Citibank (South Dakota) NA (Citigroup Incorporated)
• Original Assignee: Citibank (South Dakota) NA (Citigroup Incorporated)
• Inventors: Coleman, Ronald, Renzetti, Richard
• Primary Examiner(s): Hewitt, II, Calvin L
• Assistant Examiner(s): Winter, John M
• Application Number:
  US09/634,755
• Time in Patent Office: 4,417 Days
• Field of Search: 705/1, 705/35, 705/500, 702/35, 702/81, 717/135
• US Class Current: 705/35
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

A method and system is provided for assuring the integrity of data used to evaluate financial risk or exposure in trading portfolios such as portfolios of derivative contracts by looking for sweeping changes or statistically significant trends suggestive of possible errors. The method and system uses Content Analysis to measure the changes in the information content or entropy of data to detect abnormal changes that may require human intervention. A graphical user interface can also be provided that provides a mechanism for alerting users of possible errors and also gives an indication of the severity of the detected abnormality.

Claims

1. storing, by a server, one or more values of historical data wherein the historical data comprises at least one measurement of an investment;

receiving, by the server, via a computer network, financial input data for the investment from one or more data processing systems;

determining, by the server, a measurement for the investment based on the financial input data;

calculating, by the server, information content of the financial input data using continuous, discrete and a combination of continuous and discrete modes of the input data;

determining, by the server, a change in the information content of the financial input data as compared to information content based on the historical data;

determining, by the server, a confidence level based on the change in the information content of the financial input data as compared to the information content based on the historical data;

assessing, by the server, whether the change was caused by an error in the financial input data by categorizing the confidence level; and

generating, by the server, a report based on the categorized confidence level.

2. The method according to claim 1, wherein calculating the information content of the financial input data comprises processing non-parametric resampling statistics on changes in the information content in the financial input data.

3. The method according to claim 1, further comprising calculating the information content of the historical data by processing non-parametric resampling statistics on changes in the information content in the historical data.

4. The method according to claim 1, wherein calculating the information content of the financial input data comprises processing parametric statistics on changes in the information content in the financial input data.

5. The method according to claim 1, further comprising calculating the information content of the historical data by processing parametric statistics on changes in the information content in the historical data.

6. The method according to claim 1, wherein calculating the information content of the financial input data comprises processing Bayesian statistics on changes in the information content in the financial input data.

7. The method according to claim 1, further comprising calculating the information content of the historical data by processing Bayesian statistics on changes in the information content in the historical data.

8. The method according to claim 1, further comprising presenting the confidence level on a logarithmic scale of odds ratios.

9. The method according to claim 1, wherein determining the measurement for the investment based on the financial input data comprises deriving a mark to market or maximum likely increase in value.

10. The method according to claim 1, wherein the report comprises a symbol representing a possibility of an error in the financial input data.