Automated risk transfer system

• US 8,694,455 B2
• Filed: 07/12/2012
• Issued: 04/08/2014
• Est. Priority Date: 10/17/2000
• Status: Expired due to Fees

• Current Assignee: Jeffrey Eder
• Original Assignee: Asset Reliance Incorporated
• Inventors: Eder, Jeffrey Scott
• Primary Examiner(s): Starks, Wilbert L
• Application Number:
  US13/548,095
• Publication Number:
  US 20120303408A1
• Time in Patent Office: 635 Days
• Field of Search: 706/45
• US Class Current: 706/45
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

An automated method, computer program product and system for using artificial intelligence based cognitive learning methods to identify, measure and manage risks for a commercial enterprise on a continual basis. The elements of value, external factors, components of value and categories of value of the enterprise are analyzed and modeled using predictive models that are developed by learning from the data associated with said enterprise. Scenarios of both normal and extreme situations are also developed by learning from the data. The scenarios are then used to drive simulations of the predictive models. The output from these simulations are then used to measure a plurality of risks and complete optimization analyzes that identify the optimal mix of risk reduction activities for the enterprise. The optimal mix of risk reduction activities is then presented to the user for optional editing, rejection or acceptance.

Claims

1. A computer-implemented method for performing an analysis of financial data, comprising the steps of:

storing, in a computer readable memory, financial data related to a population of financial data records and segmented into a number of categories, wherein the categories are mutually exclusive and collectively exhaustive of the financial data, and scenario data for one or more scenarios, wherein each of the scenarios is defined at least in part by a set of variables, and wherein the scenario data for each of the scenarios comprise at least some parameter values for the set of variables;

providing a computer processor associated with the computer readable memory with a model of an organization that physically exists defined at least in part by the set of variables;

processing, with the computer processor, the financial data and the scenario data using the model to obtain an estimated model outcome distribution comprising a distribution of estimated model outcomes relating to the organization and based on the one or more scenarios; and

outputting the estimated model outcome distribution where the model of the organization is developed by learning from the financial data using an intelligent variable group modeling method and where the model of the organization comprises at least one predictive model for each of one or more components of value.

2. The computer-implemented method of claim 1, wherein the population of financial data records comprise one or more item variables and one or more factor variables obtained from one or more systems selected from the group consisting of advanced financial systems, basic financial systems, web site management systems, alliance management systems, brand management systems, customer relationship management systems, channel management systems, intellectual property management systems, process management systems, vendor management systems, operation management systems, sales management systems, human resource systems, accounts receivable systems, accounts payable systems, capital asset systems, inventory systems, invoicing systems, payroll systems, enterprise resource planning systems (ERP), material requirement planning systems (MRP), scheduling systems, supply chain management systems, quality control systems, purchasing systems, risk management systems and combinations thereof and wherein the population of financial data records further comprises one or more indicators and one or more composite variables where said indicators and composite variables are derived from the group consisting of item variables, factor variables and combinations thereof.

3. The computer-implemented method of claim 1, wherein the one or more categories of value comprise a current operation, a real option category of value and a market sentiment category of value.

4. The computer-implemented method of claim 1, wherein the processing of the financial data and the scenario data with the processor using the model to obtain the estimated model outcome distribution is repeated by one or more bots or intelligent agents in accordance with a frequency specified by a user.

5. The computer-implemented method of claim 1, wherein the method further comprises segmenting the financial data into the selected number categories before storing the financial data in the computer readable memory where the categories comprise current operation revenue, current operation expense, current operation capital change, real options and market sentiment.

6. The computer-implemented method of claim 1, wherein the model outcomes comprise measures of at least one risk.

7. The computer implemented method of claim 1, wherein developing the model of the organization by learning from the financial data using the intelligent variable group modeling method comprises developing the at least one predictive model for each of one or more components of value by:

using a plurality of predictive models and a plurality of causal models to analyze and select a portion of the data to use as a value driver when modeling the value contribution of each of one or more elements of value;

learning which model from a plurality of causal models comprises a best fit for modeling the value contribution of each of the one or more elements of value when using the selected value driver data where at least one of the one or more elements of value is represented by a variable group that comprises an input to each of the causal models;

learning which algorithm from a plurality of linear and nonlinear predictive model algorithms to include in the model for each of the components of value where at least one of the one or more elements of value is represented by a variable group that comprises an input into each of the linear and nonlinear predictive model algorithms; and

learning a relative contribution of each of the elements of value to the value of the component of value

where the plurality of causal models are selected from the group consisting of Tetrad, LaGrange, Bayesian and path analysis, where the elements of value physically exist and are selected from the group consisting of customers, equipment, partners and suppliers and where the plurality of predictive models are selected from the group consisting of classification and regression tree;

projection pursuit regression;

generalized additive model (GAM), redundant regression network;

neural network, multivariate adaptive regression splines;

linear regression; and

stepwise regression when the variable group is being used as an input to represent the at least one of the elements of value in the component of value predictive model.

8. A non-transitory computer program product tangibly embodied on a computer readable medium and comprising a program code for directing at least one computer to perform an automated risk management method, comprising:

store, in a computer readable memory, financial data related to a population of financial data records and segmented into a number of categories, wherein the categories are mutually exclusive and collectively exhaustive of the financial data, and scenario data for one or more scenarios, wherein each of the scenarios is defined at least in part by a set of variables, and wherein the scenario data for each of the scenarios comprise at least some parameter values for the set of variables;

provide a computer processor associated with the computer readable memory with a model of an organization that physically exists defined at least in part by the set of variables;

process, with the computer processor, the financial data and the scenario data using the model to obtain an estimated model outcome distribution comprising a distribution of estimated model outcomes relating to the organization and based on the one or more scenarios; and

output the estimated model outcome distribution where the model of the organization is developed by learning from the financial data using an intelligent variable group modeling method and where the model of the organization comprises at least one predictive model for each of one or more components of value.

9. The non-transitory computer program product of claim 8, wherein the wherein the population of financial data records comprise one or more item variables and one or more factor variables obtained from one or more systems selected from the group consisting of advanced financial systems, basic financial systems, web site management systems, alliance management systems, brand management systems, customer relationship management systems, channel management systems, intellectual property management systems, process management systems, vendor management systems, operation management systems, sales management systems, human resource systems, accounts receivable systems, accounts payable systems, capital asset systems, inventory systems, invoicing systems, payroll systems, enterprise resource planning systems (ERP), material requirement planning systems (MRP), scheduling systems, supply chain management systems, quality control systems, purchasing systems, risk management systems and combinations thereof and wherein the population of financial data records further comprises one or more indicators and one or more composite variables where said indicators and composite variables are derived from the group consisting of item variables, factor variables and combinations thereof.

10. The non-transitory computer program product of claim 8, wherein the one or more categories of value comprise a current operation, a real option category of value and a market sentiment category of value.

11. The non-transitory computer program product of claim 8, wherein the processing of the financial data and the scenario data with the processor using the model to obtain the estimated model outcome distribution is repeated by one or more bots or intelligent agents in accordance with a frequency specified by a user.

12. The non-transitory computer program product of claim 8, wherein the method further comprises segmenting the financial data into the selected number categories before storing the financial data in the computer readable memory where the categories comprise current operation revenue, current operation expense, current operation capital change, real options and market sentiment.

13. The non-transitory computer program product of claim 8, wherein the model outcomes comprise measures of at least one risk.

14. The non-transitory computer program product of claim 8, wherein developing the model of the organization by learning from the financial data using the intelligent variable group modeling method comprises developing the at least one predictive model for each of one or more components of value by:

using a plurality of predictive models and a plurality of causal models to analyze and select a portion of the data to use as a value driver when modeling the value contribution of each of one or more elements of value;

learning which model from a plurality of causal models comprises a best fit for modeling the value contribution of each of the one or more elements of value when using the selected value driver data where at least one of the one or more elements of value is represented by a variable group that comprises an input to each of the causal models;

learning which algorithm from a plurality of linear and nonlinear predictive model algorithms to include in the model for each of the components of value where each of the one or more elements of value are represented by a summary that comprises an input into each of the linear and nonlinear predictive model algorithms; and

learning a relative contribution of each of the elements of value to the value of the component of value

where the plurality of causal models are selected from the group consisting of Tetrad, LaGrange, Bayesian and path analysis, where the elements of value physically exist and are selected from the group consisting of customers, equipment, partners and suppliers and where the plurality of predictive models are selected from the group consisting of classification and regression tree;

projection pursuit regression;

generalized additive model (GAM), redundant regression network;

neural network, multivariate adaptive regression splines;

linear regression; and

stepwise regression when a variable group is not being used as an input to represent at least one of the elements of value in the component of value predictive model.

15. An automated risk management system, comprising:

a computer with at least one processor having circuitry to execute instructions;

a storage device available to each of said processors with sequences of instructions stored therein, which when executed cause at least one of the processors to;

store, in a computer readable memory, financial data related to a population of financial data records and segmented into a number of categories, wherein the categories are mutually exclusive and collectively exhaustive of the financial data, and scenario data for one or more scenarios, wherein each of the scenarios is defined at least in part by a set of variables, and wherein the scenario data for each of the scenarios comprise at least some parameter values for the set of variables;

provide the computer processors associated with the storage device with a model of an organization that physically exists defined at least in part by the set of variables;

process, with the computer processor, the financial data and the scenario data using the model to obtain an estimated model outcome distribution comprising a distribution of estimated model outcomes relating to the organization and based on the one or more scenarios; and

output the estimated model outcome distribution where the model of the organization is developed by learning from the financial data using an intelligent variable group modeling method and where the model of the organization comprises at least one predictive model for each of one or more components of value.

16. The system of claim 15, wherein the wherein the population of financial data records comprise one or more item variables and one or more factor variables obtained from one or more systems selected from the group consisting of advanced financial systems, basic financial systems, web site management systems, alliance management systems, brand management systems, customer relationship management systems, channel management systems, intellectual property management systems, process management systems, vendor management systems, operation management systems, sales management systems, human resource systems, accounts receivable systems, accounts payable systems, capital asset systems, inventory systems, invoicing systems, payroll systems, enterprise resource planning systems (ERP), material requirement planning systems (MRP), scheduling systems, supply chain management systems, quality control systems, purchasing systems, risk management systems and combinations thereof and wherein the population of financial data records further comprises one or more indicators and one or more composite variables where said indicators and composite variables are derived from the group consisting of item variables, factor variables and combinations thereof.

17. The system of claim 15, wherein the one or more categories of value comprise a current operation, a real option category of value and a market sentiment category of value.

18. The system of claim 15, wherein the processing of the financial data and the scenario data with the processors using the model to obtain the estimated model outcome distribution is repeated by one or more bots or intelligent agents in accordance with a frequency specified by a user.

19. The system of claim 15, the processors further segment the financial data into the selected number categories before storing the financial data in the computer readable memory where the categories comprise current operation revenue, current operation expense, current operation capital change, real options and market sentiment.

20. The system of claim 15, wherein developing the model of the organization by learning from the financial data using the intelligent variable group modeling method comprises developing the at least one predictive model for each of one or more components of value by:

using a plurality of predictive models and a plurality of causal models to analyze and select a portion of the data to use as a value driver when modeling the value contribution of each of one or more elements of value;

learning which model from a plurality of causal models comprises a best fit for modeling the value contribution of each of the one or more elements of value when using the selected value driver data where at least one of the one or more elements of value is represented by a variable group that comprises an input to each of the causal models;

learning which algorithm from a plurality of linear and nonlinear predictive model algorithms to include in the model for each of the components of value where each of the one or more elements of value are is represented by a summary that comprises an input into each of the linear and nonlinear predictive model algorithms; and

learning a relative contribution of each of the elements of value to the value of the component of value where the plurality of causal models are selected from the group consisting of Tetrad, LaGrange, Bayesian and path analysis, where the elements of value physically exist and are selected from the group consisting of customers, equipment, partners and suppliers and where the plurality of predictive models are selected from the group consisting of classification and regression tree;

projection pursuit regression;

generalized additive model (GAM), redundant regression network;

neural network, multivariate adaptive regression splines;

linear regression; and

stepwise regression when a variable group is not being used as an input to represent at least one of the elements of value in the component of value predictive model.