Unlock instant, AI-driven research and patent intelligence for your innovation.

Foreign exchange transaction method based on neural network prediction models

A neural network and prediction model technology, applied in the field of foreign exchange trading based on neural network, can solve the problems of turbulence in the foreign exchange market and complicated exchange rate factors.

Inactive Publication Date: 2010-10-06
BEIJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the foreign exchange market is turbulent, and the factors affecting the exchange rate are also complicated, giving traders a feeling of being at a loss as to how to proceed with analysis and forecasting

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Foreign exchange transaction method based on neural network prediction models
  • Foreign exchange transaction method based on neural network prediction models
  • Foreign exchange transaction method based on neural network prediction models

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to enable those skilled in the art to better understand the solutions of the embodiments of the present invention, the embodiments of the present invention will be further described in detail below in conjunction with the drawings and implementations.

[0039] The mechanical trading system is mainly divided into three subsystems, one is the market transaction signal decision-making subsystem, the other is the risk management subsystem, and the third is the fund management subsystem. Among them, the market transaction signal decision-making subsystem is the basis of the other two subsystems, and the other two subsystems output transaction signals according to the transaction signal decision-making subsystem to carry out risk management and investment management.

[0040] refer to figure 1 It is a structural schematic diagram of the mechanical trading system of the present invention. The components of the mechanical trading system are: market, position size, mark...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for building a prediction model by applying neural networks (RRL, BP and SOM neural networks) for short-termed foreign exchange transactions, and for determining to use which neural network to predict transaction signals (buy in or sell out) at a certain transaction internals through a comparison test. Wherein, the RRL neural network prediction model adopts a self-organization learning method, and outputs the sell, buy and do nothing information which is decided according to a vector F. The BP and the SOM neural network prediction models can be built by establishing and initializing network objects with MATLAB neural network toolbox functions, output and obtain three output results which respectively correspond to sell, buy and do nothing.

Description

technical field [0001] The invention relates to the financial field, in particular to a neural network-based foreign exchange transaction method. Background technique [0002] Under the conditions of today's increasingly open economy, companies, banks, governments and individuals have to face the objective existence of foreign exchange transactions, and will be actively or passively affected by exchange rate changes. When holding hard currencies, the rise in exchange rates will bring To gain; when holding soft currency, exchange rate decline will bring losses. [0003] The foreign exchange market is a fantastic place full of opportunities and challenges. It is the main source of profits for multinational companies and an important place for government departments to maintain and increase the value of foreign exchange reserves. However, the foreign exchange market is turbulent, and the factors affecting the exchange rate are also complicated, which gives traders a feeling of...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06Q90/00G06Q40/00G06N3/02G06Q40/04
Inventor 潘维民
Owner BEIJING UNIV OF POSTS & TELECOMM