Predicting economic conditions

• US 9,741,048 B2
• Filed: 05/04/2016
• Issued: 08/22/2017
• Est. Priority Date: 11/12/2013
• Status: Active Grant

• Current Assignee: Bank of America Corp.
• Original Assignee: Bank of America Corp.
• Inventors: Bendel, Timothy J., Krein, Mark V., Joffe, David N., Setiawan, Sandi, Nobili, William Anthony, Joa, David
• Primary Examiner(s): Berona, Kimberly
• Assistant Examiner(s): Jacob, William J
• Application Number:
  US15/146,137
• Publication Number:
  US 20160260114A1
• Time in Patent Office: 475 Days
• Field of Search: 706 21
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0205 Location or geographical consideration
• CPC Class Codes: G06Q 40/04 Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
• CPC Class Codes: G06Q 40/06 Asset management; Financial planning or analysis

Abstract

Computer-implemented methods for identifying or assessing any type of risk and/or opportunity that may arise can include either, alone or in combination, band pass filtering, principal component analysis, random matrix theory analysis, synchronization analysis, and early-warning detection. Each technique can also be viewed as a process that takes a set of inputs and converts it to a set of outputs. These outputs can be used as inputs for a subsequent process or the outputs may be directly actionable for formulating certain economic predictions to make certain decisions.

Claims

1. An apparatus comprising:

an early warning system;

an electronic processing device; and

a memory device storing computer readable instructions that, when executed by the electronic processing device, cause the apparatus to;

receive economic data for a plurality of time series, wherein each time series of the plurality of time series corresponds to a different geographical entity;

determine auto regressive model coefficients for the economic data of the plurality of time series;

determine, for a first time series of the plurality, a first scaled lag-1 auto-correlation of the coefficients;

determine, for the first time series, a first scaled smoothed derivative from the first scaled lag-1 auto-correlation of the coefficients;

output, for the first member, a first indicator based on the first scaled smoothed derivative;

generate, by the early warning system based on at least the first indicator for the first time series of the plurality of time series, an early warning signal, wherein the first time series corresponds only to a first geographical entity and wherein the early warning signal comprises an early warning notification and detailed information about a potential instability of the economic data;

determine a set of registered computing devices associated with the first geographical entity, wherein the set includes a first device and a second device;

send the early warning notification about the first geographical entity to the first device and second device;

initiate launching of an early warning application at the first device; and

send the detailed information about the potential instability to the first device via the early warning application.

2. The apparatus of claim 1 wherein the first indicator is positive when the first scaled smoothed derivative is above a predetermined threshold value.

3. The apparatus of claim 1 wherein the first indicator is negative when the first scaled smoothed derivative is below a predetermined threshold value.

4. The apparatus of claim 1 wherein the economic data for the plurality of time series comprises Home Price Index data.

5. The apparatus of claim 1, wherein the memory device stores computer readable instructions that, when executed by the electronic processing device, further cause the apparatus to output a second indicator based on the first scaled lag-1 auto-correlation of the coefficients and the early warning signal is based on the first indicator and the second indicator.

6. The apparatus of claim 1, wherein the memory device stores computer readable instructions that, when executed by the electronic processing device, further cause the apparatus to:

select a selected time series from the plurality of time series; and

generate the early warning signal from the first indicator of the selected time series.

7. The apparatus of claim 1, wherein the memory device stores computer readable instructions that, when executed by the electronic processing device, further cause the apparatus to:

output a second indicator based on the first scaled lag-1 auto-correlation of the coefficients;

select a selected indicator from the first and second indicators; and

generate the early warning signal from the selected indicator of the selected time series.

8. The apparatus of claim 1, wherein the plurality of time series comprises the first time series and a second time series, the second time series corresponds to a second geographical region, and the early warning signal is applicable only for the first time series.

9. The apparatus of claim 1, wherein the memory device stores computer readable instructions that, when executed by the electronic processing device, further cause the apparatus to:

send an invite message to another device, wherein the invite message invites the other device to communicate with the first device.

10. The apparatus of claim 1, wherein the memory device stores computer readable instructions that, when executed by the electronic processing device, further cause the apparatus to:

when the acknowledgment to the warning notification is received from the first device, identify a device type of the first device;

determine a first display characteristic of the first device from the device type; and

send a subset of information components to the first device based on the first display characteristic, wherein the detailed information comprises a plurality of information components.

21. The apparatus of claim 1 further comprises:

a data structure, wherein the data structure maps decision-making roles of individuals with associated device identities, wherein the device identities identify a plurality of devices; and

wherein the memory device stores computer readable instructions that, when executed by the electronic processing device, further cause the apparatus to establish a first communication connection with the plurality of devices based on the data structure.

22. The apparatus of claim 21 wherein the memory device stores computer readable instructions that, when executed by the electronic processing device, further cause the apparatus to:

establish a second communication connection with a subset of the plurality of devices based on the data structure; and

prevent content of the second communication connection from being conveyed to the first communication connection.

23. The apparatus of claim 1 wherein the memory device stores computer readable instructions that, when executed by the electronic processing device, further cause the apparatus to:

send an alert indication to a designated recipient through an access-id application, wherein the recipient is informed to check at least one of the set of registered computing devices.

11. A method comprising:

receiving economic data for a plurality of time series, wherein each time series of the plurality of time series corresponds to a different geographical entity;

determining, for a first time series of the plurality, auto regressive model coefficients for the economic data of the plurality of time series, wherein the first time series corresponds to a first geographical entity;

determining, for the first member, a scaled lag-1 auto-correlation of the coefficients;

determining a scaled smoothed derivative from the scaled lag-1 auto-correlation of the coefficients;

outputting, for the first member, a first indicator based on the scaled smoothed derivative, wherein the first indicator is applicable only to the first geographical entity;

generating, based on the first indicator for the first time series of the plurality of time series, an early warning signal via a computer network, wherein the early warning signal comprises an early warning notification and detailed information about a potential instability of the economic data;

processing the early warning signal to determine whether there is an instability of the economic data for the first geographical entity;

determining a set of registered computing devices associated with the first geographical entity, wherein the set includes a first device and a second device;

sending the early warning notification about the first geographical entity to the first device and second device;

initiating launching of an early warning application at the first device; and

sending the detailed information about the potential instability to the first device via the early warning application.

12. The method of claim 11 wherein the first indicator is positive when the scaled lag-1 auto-correlation of the coefficients is above a predetermined threshold value.

13. The method of claim 11 wherein the first indicator is negative when the scaled lag-1 auto-correlation of the coefficients is below a predetermined threshold value.

14. The method of claim 11 wherein the economic data for the time series comprises Home Price Index data.

15. The method of claim 11 further comprising:

outputting a second indicator based on the scaled smoothed derivative from the scaled lag-1 auto-correlation of the coefficients.

16. One or more non-transitory computer-readable media having instructions stored thereon that, when executed, cause at least one computing device to:

receive economic data for a plurality of a time series, wherein each time series of the plurality of time series corresponds to a different geographical entity;

determine, for a first time series of the plurality, auto regressive model coefficients for the economic data of the plurality of time series, wherein the first time series corresponds to a first geographical entity;

determine, for the first member, a scaled lag-1 auto-correlation of the coefficients;

determine a scaled smoothed derivative from the scaled lag-1 auto-correlation of the coefficients;

output, for the first time series, a first indicator based on the scaled smoothed derivative, wherein the first indicator is applicable only to the first geographical entity;

generate, based on the first indicator for the first time series, an early warning signal to an early warning system via a computer network, wherein the first times series corresponds to a first geographical entity;

determine, from the early warning signal, whether there is an instability of the economic data for the first geographical entity, wherein the early warning signal comprises an early warning notification and detailed information about a potential instability of the economic data;

determine a set of registered computing devices associated with the first geographical entity, wherein the set includes a first device and a second device;

send the early warning notification about the first geographical entity to the first device and second device;

initiate a launching of an early warning application at the first device; and

send the detailed information about the potential instability to the first device via the early warning application.

17. The one or more non-transitory computer-readable media of claim 16 wherein the first indicator is positive when the scaled lag-1 auto-correlation of the coefficients is above a predetermined threshold value.

18. The one or more non-transitory computer-readable media of claim 16 wherein the first indicator is negative when the scaled lag-1 auto-correlation of the coefficients is below a predetermined threshold value.

19. The one or more non-transitory computer-readable media of claim 16 wherein the economic data for the time series comprises Home Price Index data.

20. The one or more non-transitory computer-readable media of claim 16 wherein the at least one computing device performs:

outputting a second indicator based on the scaled smoothed derivative from the scaled lag-1 auto-correlation of the coefficients.