# US 2010/0169235 A1 · Real-Time Trade Forecaster

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2010/0169235 A1
- Document ID: US20100169235A1
- Status: Published application
- Kind: A1
- Application number: 12/344,901
- Filed: 2008-12-29
- Published: 2010-07-01
- Earliest claimed: 2008-12-29
- Assignees: Fmr LLC
- Inventors: Jacob C. Lindeman
- Web page: https://patentgrep.com/patent/US20100169235A1

## CPC

- G06Q 40/06: Asset management; Financial planning or analysis
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

Forecasting financial market activity includes a host system and a graphical processing unit in data communication with the server. Forecasting financial market activity also includes a computer program product residing on the host system, the computer program product including instructions for causing the host system to send one or more financial models to the graphical processing unit; and a computer program product residing on the graphical processing unit for causing the graphical processing unit to: receive the financial models and a list of types of market data associated with each financial model; generate one or more engine instances; structure the received market data; receive instructions, from the host system, to run an identified financial model; clone at least part of the structured market data; run the engine instances; and generate, in real time, forecast data indicative of an expected market performance.

## Claims

### Claim 1

An apparatus for forecasting financial market activity, the apparatus comprising:
a host system for receiving streamed market data indicative of financial market activity;
a graphical processing unit in data communication with the host system, wherein the graphical processing unit includes:
processor memory for receiving, from the host system, the streamed market data;
a computer program product residing on the host system, the computer program product including instructions for causing the host system to send one or more financial models to the graphical processing unit; and
a computer program product residing on the graphical processing unit for executing financial models received from the host system against the market data received from the host system, the computer program product including instructions for causing the graphical processing unit to:
receive the financial models and a list of types of market data associated with each financial model;
generate one or more engine instances based on the received financial models and the list of types of market data associated with each model;
structure the received market data according to a timestamp associated with the market data;
receive instructions, from the host system, to run an identified financial model;
clone at least part of the structured market data on the basis of the timestamps and the engine instances which are based on the identified financial model;
run the engine instances which are based on the identified financial model to generate, in real time, forecast data indicative of an expected market performance, wherein the forecast data is at least partly based on the cloned market data; and
output the forecast data indicative of an expected market performance.

### Claim 2 (depends on 1)

The apparatus of claim 1, further comprising more than one graphical processing unit in data communication with the server.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the computer program product includes instructions for causing the graphical processing unit to:
structure the received market data according to a ticker symbol associated with the market data.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the computer program product includes instructions for causing the graphical processing unit to:
execute, in parallel, more than one financial algorithm against the selected data.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein the computer program product includes instructions for causing the graphical processing unit to:
update the selected data by overwriting first selected data with second selected data.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein the computer program product includes instructions for causing the graphical processing unit to:
transfer, to the host system, the data indicative of an expected market performance.

### Claim 7 (depends on 1)

The apparatus of claim 1, wherein the computer program product includes instructions for causing the graphical processing unit to:
allocate the memory on the graphical processing unit prior to receiving streamed data indicative of financial market activity.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the computer program product includes instructions for causing the graphical processing unit to
collect statistics regarding the processing of the received data.

### Claim 9 (depends on 1)

The apparatus of claim 1, wherein the computer program product includes instructions for causing the graphical processing unit to:
generate data structures for storing the received data.

### Claim 10 (depends on 1)

The apparatus of claim 1, wherein the computer program product includes instructions for causing the graphical processing unit to:
run at least two engine instances at asynchronous times.

### Claim 11

An apparatus for forecasting financial market activity, the apparatus comprising:
a host system for receiving streamed market data indicative of financial market activity;
co-processor hardware in data communication with the host system, wherein the co-processor hardware includes:
processor memory for receiving, from the host system, the streamed market data;
a computer program product residing on the host system, the computer program product including instructions for causing the host system to send one or more financial models to the co-processor hardware; and
a computer program product residing on the co-processor hardware for executing financial models received from the host system against the market data received from the host system, the computer program product including instructions for causing the co-processor hardware to:
receive the financial models and a list of types of market data associated with each financial model;
generate one or more engine instances based on the received financial models and the list of types of market data associated with each model;
structure the received market data according to a timestamp associated with the market data;
receive instructions, from the host system, to run an identified financial model;
clone at least part of the structured market data on the basis of the timestamps and the engine instances which are based on the identified financial model;
run the engine instances which are based on the identified financial model to generate, in real time, forecast data indicative of an expected market performance, wherein the forecast data is at least partly based on the cloned market data; and
output the forecast data indicative of an expected market performance.

### Claim 12

An apparatus for forecasting financial market activity, the apparatus comprising:
a graphical processing unit that interfaces with a market data source, wherein the graphical processing unit includes:
processor memory for receiving streamed market data;
a computer program product residing on the graphical processing unit for executing financial models against the market data, the computer program product including instructions for causing the graphical processing unit to:
receive market data from the market data source;
receive, from a host system, the financial models and a list of types of market data associated with each financial model;
generate one or more engine instances based on the received financial models and the list of types of market data associated with each model;
structure the received market data according to a timestamp associated with the market data;
receive instructions to run an identified financial model;
clone at least part of the structured market data on the basis of the timestamps and the engine instances which are based on the identified financial model;
run the engine instances which are based on the identified financial model to generate, in real time, forecast data indicative of an expected market performance, wherein the forecast data is at least partly based on the cloned market data; and
output the forecast data indicative of an expected market performance.

### Claim 13

A computer-implemented method for forecasting financial market activity, the method comprising:
receiving, on a graphical processing unit, streamed market data indicative of financial market activity;
receiving financial models and a list of types of market data associated with each financial model;
generating one or more engine instances based on the received financial models and the list of types of market data associated with each model;
structuring the received market data according to a timestamp associated with the market data;
receiving instructions, from a host system, to run an identified financial model;
cloning at least part of the structured market data on the basis of the timestamps and the engine instances which are based on the identified financial model;
running the engine instances which are based on the identified financial model to generate, in real time, forecast data indicative of an expected market performance, wherein the forecast data is at least partly based on the cloned market data; and
outputting the forecast data indicative of an expected market performance.

### Claim 14 (depends on 13)

The method of claim 13, further comprising:
structuring the received market data according to a ticker symbol associated with the market data.

### Claim 15 (depends on 13)

The method of claim 13, further comprising:
executing, in parallel, more than one financial algorithm against the selected data.

### Claim 16 (depends on 13)

The method of claim 13, further comprising:
updating the selected data by overwriting first selected data with second selected data.

### Claim 17 (depends on 13)

The method of claim 13, further comprising:
transferring, to the host system, the data indicative of an expected market performance.

### Claim 18 (depends on 13)

The method of claim 13, further comprising:
allocating the memory on the graphical processing unit prior to receiving streamed data indicative of financial market activity.

### Claim 19 (depends on 13)

The method of claim 13, further comprising:
collecting statistics regarding the processing of the received data.

### Claim 20 (depends on 13)

The method of claim 13, further comprising:
generating data structures for storing the received data.

### Claim 21 (depends on 13)

The method of claim 13, further comprising:
running at least two engine instances at asynchronous times.

### Claim 22

A computer readable medium having encoded thereon software for forecasting financial market activity, the software comprising instructions for causing a graphical processing unit to:
receive, from a host system, streamed market data indicative of financial market activity;
receive financial models and a list of types of market data associated with each financial model;
generate one or more engine instances based on the received financial models and the list of types of market data associated with each model;
structure the received market data according to a timestamp associated with the market data;
receive instructions, from the host system, to run an identified financial model;
clone at least part of the structured market data on the basis of the timestamps and the engine instances which are based on the identified financial model;
run the engine instances which are based on the identified financial model to generate, in real time, forecast data indicative of an expected market performance, wherein the forecast data is at least partly based on the cloned market data; and
output the forecast data indicative of an expected market performance.

### Claim 23 (depends on 22)

The computer-readable medium of claim 22, wherein the software further comprises instructions for causing a graphical processing unit to:
structure the received market data according to a ticker symbol associated with the market data.

### Claim 24 (depends on 22)

The computer-readable medium of claim 22, wherein the software further comprises instructions for causing a graphical processing unit to:
execute, in parallel, more than one financial algorithm against the selected data.

### Claim 25 (depends on 22)

The computer-readable medium of claim 22, wherein the software further comprises instructions for causing a graphical processing unit to:
update the selected data by overwriting first selected data with second selected data.

### Claim 26 (depends on 22)

The computer-readable medium of claim 22, wherein the software further comprises instructions for causing a graphical processing unit to:
transfer, to the host system, the data indicative of an expected market performance.

### Claim 27 (depends on 22)

The computer-readable medium of claim 22, wherein the software further comprises instructions for causing a graphical processing unit to:
allocate the memory on the graphical processing unit prior to receiving streamed data indicative of financial market activity.

### Claim 28 (depends on 22)

The computer-readable medium of claim 22, wherein the software further comprises instructions for causing a graphical processing unit to:
collect statistics regarding the processing of the received data.

### Claim 29 (depends on 22)

The computer-readable medium of claim 22, wherein the software further comprises instructions for causing a graphical processing unit to:
generate data structures for storing the received data.

### Claim 30 (depends on 22)

The computer-readable medium of claim 22, wherein the software further comprises instructions for causing a graphical processing unit to:
run at least two engine instances at asynchronous times.
