An empirical study of volatility predictions: stock market analysis using neural networks

Authors:
Bernard Fong;A. C. M. Fong;G. Y. Hong;Louisa Wong
Affiliations:
Auckland University of Technology, Auckland, New Zealand;School of Computer Engineering, Nanyang Technological University, Singapore;Institute of Information & Mathematics Sciences, Massey University, Auckland, New Zealand;Manulife Asset Management, Hong Kong
Venue:
WINE'05 Proceedings of the First international conference on Internet and Network Economics
Year:
2005

Citing 6
Cited 0

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Neural Networks: Current Applications

Neural Networks: Current Applications
Neural Networks in Finance and Investing: Using Artificial Intelligence to Improve Real World Performance

Neural Networks in Finance and Investing: Using Artificial Intelligence to Improve Real World Performance
On performance of an equalization algorithm based on space and time diversity for wireless multimedia services to home users

IEEE Transactions on Consumer Electronics
Optimal adaptive multiuser detection in unknown multipath channels

IEEE Journal on Selected Areas in Communications
Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Volatility is one of the major factor that causes uncertainty in short term stock market movement. Empirical studies based on stock market data analysis were conducted to forecast the volatility for the implementation and evaluation of statistical models with neural network analysis. The model for prediction of Stock Exchange short term analysis uses neural networks for digital signal processing of filter bank computation. Our study shows that in the set of four stocks monitored, the model based on moving average analysis provides reasonably accurate volatility forecasts for a range of fifteen to twenty trading days.