Application of bayesian techniques for MLPs to financial time series forecasting

Authors:
Andrew Skabar
Affiliations:
Department of Computer Science and Computer Engineering, La Trobe University, Bundoora, VIC, Australia
Venue:
AI'05 Proceedings of the 18th Australian Joint conference on Advances in Artificial Intelligence
Year:
2005

Citing 3
Cited 1

A practical Bayesian framework for backpropagation networks

Neural Computation
Bayesian Learning for Neural Networks

Bayesian Learning for Neural Networks
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition

Trading strategy design in financial investment through a turning points prediction scheme

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Bayesian learning techniques for MLPs are applied to the problem of forecasting the direction of change in daily close values of the Australian All Ordinaries Index. Predictions made over a 13 year out-of-sample period were tested against two null hypotheses—the null hypothesis of a mean accuracy of 0.5 (which is the expected accuracy if prices follow a random walk), and a null hypothesis which takes into account non-stationarity in the prices series. Results show that both null hypotheses can be rejected at the 0.005 level, but much more confidently in the case of the Bayesian approach as compared to an approach using conventional gradient descent based weight optimization.