Applicability of information criteria for neural network architecture selection

Christian Haefke, Christian Helmenstein

Research output: Contribution to conferencePaper

Abstract

In most of the empirical research on capital markets, stock market indexes are used as proxies for the aggregate market development. In previous work we found that a particular market segment of the Vienna stock exchange might be less efficient than the whole market and hence easier to forecast. Extending the focus of investigation in this paper, we use feedforward networks and linear models to predict the all share index WBI as well as various subindexes covering the highly liquid, semi-liquid, and initial public offering (IPO) market segment. In order to shed some light on network construction principles, we compare different models as selected by hold-out crossvalidation (HCV), Akaike's information criterion (AIC), and Schwartz' information criterion (SIC). The forecasts are subsequently evaluated on the basis of hypothetical trading in the out-of-sample period.

Original languageEnglish (US)
Pages293-301
Number of pages9
Publication statusPublished - Dec 1 1996
EventProceedings of the IEEE/IAFE 1996 Conference on Computational Intelligence for Financial Engineering, CIFEr - New York, NY, USA
Duration: Mar 24 1996Mar 26 1996

Other

OtherProceedings of the IEEE/IAFE 1996 Conference on Computational Intelligence for Financial Engineering, CIFEr
CityNew York, NY, USA
Period3/24/963/26/96

    Fingerprint

ASJC Scopus subject areas

  • Computer Science(all)
  • Economics, Econometrics and Finance(all)
  • Engineering(all)

Cite this

Haefke, C., & Helmenstein, C. (1996). Applicability of information criteria for neural network architecture selection. 293-301. Paper presented at Proceedings of the IEEE/IAFE 1996 Conference on Computational Intelligence for Financial Engineering, CIFEr, New York, NY, USA, .