U.S. patents available from 1976 to present.
U.S. patent applications available from 2005 to present.

Predictive neural network means and method for selecting a portfolio of securities wherein each network has been trained using data relating to a corresponding security

Patent 5761442 Issued on June 2, 1998. Estimated Expiration Date: Icon_subject June 2, 2015. Estimated Expiration Date is calculated based on simple USPTO term provisions. It does not account for terminal disclaimers, term adjustments, failure to pay maintenance fees, or other factors which might affect the term of a patent.

Patent References

Securities brokerage-cash management system obviating float costs by anticipatory liquidation of short term assets
Patent #: 4597046
Issued on: 06/24/1986
Inventor: Musmanno ,   et al.

Special purpose neurocomputer system for solving optimization problems
Patent #: 4858147
Issued on: 08/15/1989
Inventor: Conwell

Probabilistic inference gate
Patent #: 5077677
Issued on: 12/31/1991
Inventor: Murphy, et al.

Method and a system for selection of time series data
Patent #: 5109475
Issued on: 04/28/1992
Inventor: Kosaka, et al.

Neural network with weight adjustment based on prior history of input signals
Patent #: 5119469
Issued on: 06/02/1992
Inventor: Alkon, et al.

Marketing research method and system for management of manufacturer's discount coupon offers
Patent #: 5245533
Issued on: 09/14/1993
Inventor: Marshall

Elevator control apparatus using neural network to predict car direction reversal floor
Patent #: 5250766
Issued on: 10/05/1993
Inventor: Hikita, et al.

Computer aided real-time decision support system and method Patent #: 5267148
Issued on: 11/30/1993
Inventor: Kosaka, et al.

Inventors

Assignee

Application

No. 298905 filed on 08/31/1994

US Classes:

705/35Finance (e.g., banking, investment or credit)

Examiners

Primary: Chin, Tommy P.
Assistant: Vincent, David

Attorney, Agent or Firm

Foreign Patent References

  • 2 253 081 GB. 08/12/1992

International Class

H01J 001/00

Abstract

A data processing system and method for selecting securities and constructing an investment portfolio is based on a set of artificial neural networks which are designed to model and track the performance of each security in a given capital market and output a parameter which is related to the expected risk adjusted return for the security. Each artificial neural network is trained using a number of fundamental and price and volume history input parameters about the security and the underlying index. The system combines the expected return/appreciation potential data for each security via an optimization process to construct an investment portfolio which satisfies predetermined aggregate statistics. The data processing system receives input from the capital market and periodically evaluates the performance of the investment portfolio, rebalancing it whenever necessary to correct performance degradations.

Other References

  • Ankrim, Ernest et al., Multicurrency Performance Attribution, Financial Analysts Journal, pp. 1-1-14 (renumbered by examiner), Mar. 1994
  • Morningstar, Inc. User's Guide to Morningstar Mutual Funds, pp. 11-12, 13-16, 22-24 and 41-43, Apr. 29, 1994
  • NeuroForecaster, "The NeuroForecaster.RTM. Way to Analyze, Classify and Forecast," A Professional Business Forecasting Tool Guide, Singapore, 1993
  • David E. Rumelhart, James L. McClelland, "Parallel Distributed Processing Explorations in the Microstructure of Cognition vol. 1: Foundations," Chapter 8, the MIT Press, Cambridge, Massachusetts, 1987
  • NeuroShell.RTM. 2 Users Manual, Ward Systems Group, Inc., Chapter 5, pp. 123-143, 1993
  • Fishman, Mark B., Barr, Dean S., Heavner, Ellen, "A New Perspective on Conflict Resolution in Market Forecasting," IEEE Computer Society Press Reprint from Proc. of The First International Conference On Artificial Intelligence Applications On Wall Street, pp. 97-102, New York, Oct. 9-11, 1991
  • Fishman, Mark B., Deans S. Barr and Walter J. Loick, "Using Neural Nets in Market Analysis", reprinted from Technical Analysis of Stocks & Commodities™ magazine, 1991
  • Barr, Dean S., Mani, Ganesh, "Neural Nets in Investment Management: Multiple Users," Software Engineering Press, 199
PatentsPlus Images
Enhanced PDF formats
loading...
PatentsPlus: add to cart
PatentsPlus: add to cartSearch-enhanced full patent PDF image
$9.95more info
PatentsPlus: add to cart
PatentsPlus: add to cartIntelligent turbocharged patent PDFs with marked up images
$18.95more info
 
Sign InRegister
Username  
Password   
forgot password?