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

Nathan L. Joseph, David S. Brée, Efstathios Kalyvas

Research output: Contribution to journalArticlepeer-review


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.
Original languageEnglish
Pages (from-to)93-125
Number of pages33
JournalAdvances in Econometrics
Publication statusPublished - 2004


  • learning procedures
  • genetic algorithms
  • GAs
  • optimal architectures
  • artificial neural networks
  • ANNs
  • high frequency data
  • daily excess stock returns
  • excess returns


Dive into the research topics of 'Using non-parametric search algorithms to forecast daily excess stock returns'. Together they form a unique fingerprint.

Cite this