Using non-parametric search algorithms to forecast daily excess stock returns

Joseph, Nathan L., Brée, David S. and Kalyvas, Efstathios (2004). Using non-parametric search algorithms to forecast daily excess stock returns. Advances in Econometrics, 19 , pp. 93-125.

Abstract

Are the learning procedures of genetic algorithms (GAs) able to generate optimal architectures for artificial neural networks (ANNs) in high frequency data? In this experimental study,GAs are used to identify the best architecture for ANNs. Additional learning is undertaken by the ANNs to forecast daily excess stock returns. No ANN architectures were able to outperform a random walk,despite the finding of non-linearity in the excess returns. This failure is attributed to the absence of suitable ANN structures and further implies that researchers need to be cautious when making inferences from ANN results that use high frequency data.

Publication DOI: https://doi.org/10.1016/S0731-9053(04)19004-X
Divisions: Aston Business School > Accounting
Aston Business School > Accounting Research Group
Uncontrolled Keywords: learning procedures,genetic algorithms,GAs,optimal architectures,artificial neural networks,ANNs,high frequency data,daily excess stock returns,excess returns
Full Text Link: http://www.emer ... 4&show=abstract
Related URLs:
Published Date: 2004
Authors: Joseph, Nathan L. ( 0000-0002-2182-0847)
Brée, David S.
Kalyvas, Efstathios

Export / Share Citation


Statistics

Additional statistics for this record