A dynamic meta-learning rate-based model for gold market forecasting

Authors:
Shifei Zhou;Kin Keung Lai;Jerome Yen
Affiliations:
Department of Management Sciences, College of Business, City University of Hong Kong, Kowloon, Hong Kong;Department of Management Sciences, College of Business, City University of Hong Kong, Kowloon, Hong Kong;Department of Finance, Hong Kong University of Science and Technology, Kowloon, Hong Kong
Venue:
Expert Systems with Applications: An International Journal
Year:
2012

Citing 10
Cited 0

Multilayer feedforward networks are universal approximators

Neural Networks
Connectionist nonparametric regression: multilayer feedforward networks can learn arbitrary mappings

Neural Networks
On-line learning in neural networks

On-line learning in neural networks
A perspective view and survey of meta-learning

Artificial Intelligence Review
Forecasting stock market movement direction with support vector machine

Computers and Operations Research
A novel nonlinear ensemble forecasting model incorporating GLAR and ANN for foreign exchange rates

Computers and Operations Research
A Hybrid ARCH-M and BP Neural Network Model For GSCI Futures Price Forecasting

ICCS '07 Proceedings of the 7th international conference on Computational Science, Part III: ICCS 2007
Oil Price Forecasting with an EMD-Based Multiscale Neural Network Learning Paradigm

ICCS '07 Proceedings of the 7th international conference on Computational Science, Part III: ICCS 2007
Surveying stock market forecasting techniques - Part II: Soft computing methods

Expert Systems with Applications: An International Journal
Integrating independent component analysis-based denoising scheme with neural network for stock price prediction

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	12.05

Visualization

Abstract

In this paper, an improved EMD meta-learning rate-based model for gold price forecasting is proposed. First, we adopt the EMD method to divide the time series data into different subsets. Second, a back-propagation neural network model (BPNN) is used to function as the prediction model in our system. We update the online learning rate of BPNN instantly as well as the weight matrix. Finally, a rating method is used to identify the most suitable BPNN model for further prediction. The experiment results show that our system has a good forecasting performance.