Intermarket analysis

• US 8,442,891 B2
• Filed: 12/07/2009
• Issued: 05/14/2013
• Est. Priority Date: 12/07/2009
• Status: Active Grant

• Current Assignee: Predictive Technologies
• Original Assignee: Predictive Technologies
• Inventors: Mendelsohn, Louis B.
• Primary Examiner(s): Patel, Jagdish
• Assistant Examiner(s): HAMILTON, SARA CHANDLER
• Application Number:
  US12/632,186
• Publication Number:
  US 20110137781A1
• Time in Patent Office: 1,254 Days
• Field of Search: 705 35- 37
• US Class Current: 705/36.R
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes

Abstract

A method and a system for performing intermarket analysis. The method can include, from a pool of available markets in which at least one key intermarket has been selected and removed, selecting at least one market as a general intermarket, and removing the market selected as the general intermarket from the pool of available markets. From the pool of available markets from which the general intermarket has been removed, at least one market can be selected as a predictive intermarket and removed from the pool of available markets. Market data for each of the key intermarket, the general intermarket and the predictive intermarket can be processed to train a neural network. After training the neural network, market data for the primary market can be processed with the neural network to predict future market data for the primary market. The predicted future market data can be output.

Claims

1. A method of obtaining predicted future market data for a primary market using a computer comprising a neural network, the method comprising the steps of:

processing training data inputted to the neural network until the neural network is trained to generate predictive output data that is close to the actual market data for the primary market, the training data comprising market data for at least one key intermarket of the primary market, market data for at least one general intermarket of the primary market, and market data for at least one predictive intermarket of the primary market, wherein (i) the at least one key market comprises at least one market known to have the most influence on the supply/demand outcome of the primary market, is selected from a first pool of intermarkets, and is removed from the first pool of intermarkets to yield a second pool of intermarkets;

(ii) the at least one general intermarket comprises the market in the second pool that best correlates with the primary market, is selected from the second pool of intermarkets, and is removed from the second pool of intermarkets to yield a third pool of intermarkets;

(iii) and the at least one predictive intermarket comprises the market in the third pool of intermarkets whose price activity most closely leads that of the primary market;

using the trained neural network to process market data for the primary market inputted to the trained neural network to obtain predicted future market data for the primary market; and

outputting the predicted future market data from the trained neural network.

2. A system for obtaining predicted future market data for a primary market, the system comprising a processor comprising a neural network, the processor configured to:

process training data inputted to the neural network until the neural network is trained to generate predictive output data that is close to the actual market data for the primary market, the training data comprising market data for at least one key intermarket of the primary market, market data for at least one general intermarket of the primary market, and market data for at least one predictive intermarket of the primary market, wherein (i) the at least one key market comprises at least one market known to have the most influence on the supply/demand outcome of the primary market, is selected from a first pool of intermarkets, and is removed from the first pool of intermarkets to yield a second pool of intermarkets;

(ii) the at least one general intermarket comprises the market in the second pool that best correlates with the primary market, is selected from the second pool of intermarkets, and is removed from the second pool of intermarkets to yield a third pool of intermarkets;

(iii) and the at least one predictive intermarket comprises the market in the third pool of intermarkets whose price activity most closely leads that of the primary market;

process market data for the primary market inputted to the trained neural network to obtain predicted future market data for the primary market; and

output the predicted future market data.

3. A computer program product comprising:

a non-transitory, computer-usable medium comprising computer-usable program code that uses a neural network to perform intermarket analysis to predict future market data for a primary market, the computer-usable medium comprising;

executable computer-usable program code that processes training data inputted to the neural network until the neural network is trained to generate predictive output data that is close to the actual market data for the primary market, the training data comprising market data for at least one key intermarket of the primary market, market data for at least one general intermarket of the primary market, and market data for at least one predictive intermarket of the primary market, wherein (i) the at least one key market comprises at least one market known to have the most influence on the supply/demand outcome of the primary market, is selected from a first pool of intermarkets, and is removed from the first pool of intermarkets to yield a second pool of intermarkets;

(ii) the at least one general intermarket comprises the market in the second pool that best correlates with the primary market, is selected from the second pool of intermarkets, and is removed from the second pool of intermarkets to yield a third pool of intermarkets;

(iii) and the at least one predictive intermarket comprises the market in the third pool of intermarkets whose price activity most closely leads that of the primary market;

executable computer-usable program code that, after the neural network is trained, processes market data for the primary market inputted to the trained neural network to obtain predicted future market data for the primary market; and

executable computer-usable program code that outputs the predicted future market data.