A Robust and Accurate Neural Predictive Model for Foreign Exchange Market Modelling and Forecasting

In this work, a robust and accurate neural predictive model based on a randomized neural learning scheme is developed for foreign exchange market modelling and forecasting purpose. In our predictive model, a dynamic single-hidden layer feedforward neural network (SLFN) is constructed with tapped-delay-memories applied at its input layer. A modified sigmoid function is designed and input weights and hidden biases are randomly assigned in such a way that highly coupled financial input patterns can be represented in the hidden feature space in a clearer way and sensitivities of the network’s hidden outputs to the changes in the financial input signals are enhanced. Also, a large number of hidden nodes in the hidden layer is used to improve the clarity of input patterns’ representation in the hidden feature space. Output weights of the network are optimized using regularised batch-learning type of least square method to improve robustness of the predictive model against external and internal disturbances. Simulation results show excellent performance of the developed model in both target deviation and directional performance measurements.

• Publication year

  2018

• Venue

  Australian and New Zealand Control Conference

• Publication date

  2018-12-01

• Fields of study

  Computer Science, Economics

• Identifiers
  DOI 10.1109/ANZCC.2018.8606555
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Performance evaluation of series and parallel strategies for financial time series forecasting

  2017cited by this paper
• A survey of randomized algorithms for training neural networks

  2016cited by this paper
• Forecasting exchange rate using deep belief networks and conjugate gradient method

  2015cited by this paper
• High Frequency Data and Volatility in Foreign Exchange Rates

  2013cited by this paper
• Robust Single-Hidden Layer Feedforward Network-Based Pattern Classifier

  2012cited by this paper
• Global Asymptotic Stability for a Class of Generalized Neural Networks With Interval Time-Varying Delays

  2011cited by this paper
• A new robust training algorithm for a class of single-hidden layer feedforward neural networks

  2011cited by this paper
• Regularized Extreme Learning Machine

  2009cited by this paper
• Financial Valuation and Risk Management Working Paper No . 590 Liquidity in the Foreign Exchange Market : Measurement , Commonality , and Risk Premiums

  2009cited by this paper
• A hybrid approach based on neural networks and genetic algorithms for detecting temporal patterns in stock markets

  2007cited by this paper
• Neural Networks in Finance and Economics Forecasting

  2007cited by this paper
• Extreme learning machine: Theory and applications

  2006cited by this paper
• MODELLING ASYMMETRIC EXCHANGE RATE DEPENDENCE a

  2006cited by this paper
• Machine Learning Techniques and Use of Event Information for Stock Market Prediction: A Survey and Evaluation

  2005cited by this paper
• A novel nonlinear ensemble forecasting model incorporating GLAR and ANN for foreign exchange rates

  2005cited by this paper
• News Announcements, Market Activity and Volatility in the Euro/Dollar Foreign Exchange Market

  2005cited by this paper
• Forecasting Foreign Exchange Rates With Artificial Neural Networks: A Review

  2004cited by this paper
• Time series forecasting using a hybrid ARIMA and neural network model

  2003cited by this paper
• Specification and Estimation of Spatial Panel Data Models

  2003cited by this paper
• Micro Effects of Macro Announcements: Real-Time Price Discovery in Foreign Exchange

  2003cited by this paper
• Official Intervention in the Foreign Exchange Market: Is it Effective, and, If so, How Does it Work?

  2001cited by this paper
• Time Delay Neural Networks Designed Using Genetic Algorithms for Short Term Inter-City Traffic Forecasting

  2001cited by this paper
• Importance of technical and fundamental analysis in the European foreign exchange market

  2001cited by this paper
• Identification and control of dynamic systems using recurrent fuzzy neural networks

  2000cited by this paper
• A survey of market practitioners' views on exchange rate dynamics

  2000cited by this paper
• Neural networks for classification: a survey

  2000cited by this paper
• The determinants of foreign exchange rate exposure: Evidence on Japanese firms 1 This paper started

  1998cited by this paper
• A Bivariate Causality between Stock Prices and Exchange Rates: Evidence from Recent Asia Flu

  1998cited by this paper
• On the "Identification and control of dynamical systems using neural networks"

  1997cited by this paper
• Public information releases, private information arrival and volatility in the foreign exchange market

  1997cited by this paper
• Predictive Data Mining: A Practical Guide

  1997cited by this paper
• Neuro-Dynamic Programming : An Overview

  1995cited by this paper
• On bias, inconsistency and efficiency of various estimators in dynamic panel data models

  1995cited by this paper
• Neural Networks: A Comprehensive Foundation

  1994cited by this paper
• Estimation of foreign exchange exposure: an application to mining companies in Australia

  1994cited by this paper
• Specification, Estimation, and Evaluation of Smooth Transition Autoregressive Models

  1994cited by this paper
• Forecasting exchange rates using feedforward and recurrent neural networks

  1992cited by this paper
• Neural networks for control systems - A survey

  1992cited by this paper
• Testing for Nonlinear Dependence in Daily Foreign Exchange Rates

  1989cited by this paper
• Economic prediction using neural networks: the case of IBM daily stock returns

  1988cited by this paper
• Time series analysis, forecasting and control

  1972cited by this paper
• survey of the

  year unknowncited by this paper

• No citing papers are available for this paper.