Computing scenario forecasts using electronic inputs

• US 10,460,010 B2
• Filed: 07/05/2016
• Issued: 10/29/2019
• Est. Priority Date: 07/05/2016
• Status: Active Grant

• Current Assignee: Oracle Financial Services Software Limited (Oracle Corporation)
• Original Assignee: Oracle Financial Services Software Limited (Oracle Corporation)
• Inventors: Murthy, Bhanu Prashanthi, Pedapudi, Lakshmi Narayana, Venketaraman, Aravind, Jagannath, Kiran, Desai, Ranveer
• Primary Examiner(s): Gebresilassie, Kibrom K
• Application Number:
  US15/201,871
• Publication Number:
  US 20180011952A1
• Time in Patent Office: 1,211 Days
• Field of Search: None
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• 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 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/06 Asset management; Financial planning or analysis

Abstract

Systems, methods, and other embodiments associated with computing scenario forecasts according to electronic inputs are described. In one embodiment, a method includes, in response to receiving a signal that triggers data collection, collecting electronic data from one or more electronic databases by aggregating the electronic data into data structures of a processing table. The electronic data defines historic values of a set of instruments. The method also includes computing projected values for each of the set of instruments according to correlations identified in the historic values. The projected values form primary forecasts that model expected future values of the set of instruments. The method includes, in response to receiving electronic inputs including scenario variables of a scenario that affects the primary forecasts, generating scenario forecasts for the set of instruments according to the scenario variables and the projected values to identify how the scenario influences the primary forecasts.

Claims

1. A non-transitory computer-readable medium storing instructions that when executed by one or more processors of a computing device cause the computing device to perform at least:

in response to receiving a signal that triggers the computing device to initiate data collection, collecting electronic data from one or more electronic databases by aggregating the electronic data into data structures of a processing table, wherein the electronic data defines historic values of a set of instruments that are different measures for an electronic account;

computing projected values for each of the set of instruments according to correlations identified in the historic values, wherein the projected values form primary forecasts that model expected future values of the set of instruments;

in response to receiving electronic inputs including scenario variables of a scenario that affects the primary forecasts, generating scenario forecasts for the set of instruments according to the scenario variables and the projected values to identify how the scenario influences the primary forecasts; and

transmitting the primary forecasts and the scenario forecasts to a remote device to cause the remote device to display the primary forecasts along with the scenario forecasts on a graphical user interface (GUI) that provides the primary forecasts and the scenario forecasts for comparison in a single display.

2. The non-transitory computer-readable medium of claim 1, wherein the instructions that cause the computing device to perform the generating of the scenario forecasts include instructions that cause the computing device to perform:

modifying coefficients determined from the computing according to the scenario variables, and

generating values of the scenario forecasts according to the modified coefficients and interdependencies identified by the primary forecasts between the set of instruments using a stochastic algorithm.

3. The non-transitory computer-readable medium of claim 1,

wherein the historic values include past trends in values of the set of instruments,

wherein the set of instruments are financial instruments that summarize profitability for separate portions of the account, and

wherein the instructions that cause the computing device to perform the computing of the primary forecasts include instructions that cause the computing device to perform:

generating the projected values over a time series for each of the set of instruments that indicates a time period and frequency of data points for the primary forecasts.

4. The non-transitory computer-readable medium of claim 1, wherein the instructions that cause the computing device to perform the computing include instructions that cause the computing device to perform the computing of the primary forecasts by using the historic values as an input to an autoregressive integrated moving average (ARIMA) model that extrapolates the projected values according to calculated coefficients that characterize patterns in the historic values of the set of instruments.

5. The non-transitory computer-readable medium of claim 1, wherein the instructions that cause the computing device to perform the collecting include instructions that cause the computing device to perform identifying that the electronic data is related to at least one of the set of instruments for the account when collecting the electronic data from the one or more electronic databases.

6. The non-transitory computer-readable medium of claim 1, wherein the scenario variables are electronic data inputs stored in electronic data structures that represent stressors on the set of instruments, wherein the scenario variables cause the computing device to alter how the projected values are extrapolated over a time series as caused by an occurrence of the scenario when generating the scenario forecasts.

7. The non-transitory computer-readable medium of claim 1, further comprising instructions that cause the computing device to perform at least:

storing, in the processing table in a memory, the scenario forecasts and the primary forecasts to organize comparisons between the scenario forecasts and the primary forecasts, wherein the scenario forecasts are generated to analyze effects on the set of instruments associated with an occurrence of the scenario.

8. A computing system, comprising:

a processor;

a non-transitory memory communicably coupled with the processor and storing at least a scenario module including instructions that when executed by the processor cause the processor to;

in response to receiving a signal that triggers the processor to initiate data collection, collect electronic data from one or more electronic databases by aggregating the electronic data into data structures of a processing table, wherein the electronic data defines historic values of a set of instruments that are different measures for an account;

compute projected values for each of the set of instruments according to correlations identified in the historic values, wherein the projected values form primary forecasts that model expected future values of the set of instruments;

in response to receiving electronic inputs including scenario variables of a scenario that affects the primary forecasts, generate scenario forecasts for the set of instruments according to the scenario variables and the projected values to identify how the scenario influences the primary forecasts; and

transmit the primary forecasts and the scenario forecasts to a remote device to cause the remote device to display the primary forecasts along with the scenario forecasts on a graphical user interface (GUI) that provides the primary forecasts and the scenario forecasts for comparison in a single display.

9. The computing system of claim 8, wherein scenario module is configured to generate the scenario forecasts by:

modifying coefficients determined from computing the projected values using the scenario variables, and

generating values of the scenario forecasts according to the modified coefficients and interdependencies identified by the primary forecasts between the set of instruments using a stochastic algorithm.

10. The computing system of claim 8,

wherein the historic values include past trends in values of the set of instruments,

wherein the set of instruments are financial instruments that summarize profitability for separate portions of the account,

wherein the scenario module is configured to compute the projected values by generating the projected values over a time series for each of the set of instruments, and

wherein the time series indicates a time period and frequency of data points for the primary forecasts.

11. The computing system of claim 8,

wherein the scenario module is configured to compute of the primary forecasts by using the historic values as an input to an autoregressive integrated moving average (ARIMA) model that extrapolates the projected values according to calculated coefficients that characterize patterns in the historic values of the set of instruments, and

wherein the scenario module is configured to collect the historic values by identifying that the electronic data is related to at least one of the set of instruments for the account.

12. The computing system of claim 8,

wherein the scenario variables are electronic data inputs that represent stressors on the set of instruments,

wherein the scenario module is configured to cause the processor to alter how the projected values are extrapolated over a time series according to the scenario variables to model an occurrence of the scenario.

13. A computer-implemented method, the method comprising:

in response to receiving, in a computing device, a signal that triggers data collection, collecting electronic data from one or more electronic databases by aggregating the electronic data into data structures of a processing table, wherein the electronic data defines historic values of a set of instruments that are different measures for an account;

computing projected values for each of the set of instruments according to correlations identified in the historic values, wherein the projected values form primary forecasts that model expected future values of the set of instruments;

in response to receiving electronic inputs including scenario variables of a scenario that affects the primary forecasts, generating scenario forecasts for the set of instruments according to the scenario variables and the projected values to identify how the scenario influences the primary forecasts; and

transmitting the primary forecasts and the scenario forecasts to a remote device to cause the remote device to display the primary forecasts along with the scenario forecasts on a graphical user interface (GUI) that provides the primary forecasts and the scenario forecasts for comparison in a single display.

14. The computer-implemented method of claim 13, wherein generating the scenario forecasts includes:

modifying coefficients determined from the computing according to the scenario variables, and

generating values of the scenario forecasts according to the modified coefficients and interdependencies identified by the primary forecasts between the set of instruments using a stochastic algorithm.

15. The computer-implemented method of claim 13,

wherein the historic values include past trends in values of the set of instruments,

wherein the set of instruments are financial instruments that summarize profitability for separate portions of the account, and

wherein computing includes generating the projected values over a time series for each of the set of instruments that indicates a time period and frequency of data points for the primary forecasts.

16. The computer-implemented method of claim 13,

wherein the scenario variables are electronic data inputs stored in electronic data structures that represent stressors on the set of instruments,

wherein the scenario variables cause the computing device to alter how the projected values are extrapolated over a time series as caused by an occurrence of the scenario when generating the scenario forecasts.

17. The computer-implemented method of claim 13, wherein the instructions that cause the computing device to perform the computing include instructions that cause the computing device to perform the computing of the primary forecasts by using the historic values as an input to an autoregressive integrated moving average (ARIMA) model that extrapolates the projected values according to calculated coefficients that characterize patterns in the historic values of the set of instruments.